Highlights of Data Science (GDS) Talks @ APS 2024 March Meeting
American Physics Society (APS) March meeting is one of the largest physics meetings in the world. To help the community quickly catch up on the work presented in this conference, Paper Digest Team processed all accepted work, and generated one highlight sentence (typically the main topic) for each. Readers are encouraged to read these machine generated highlights to quickly get the main idea of each piece of work.
Interested users can choose to read all APS-2024 presentations in our digest console, which supports more features.
To search for work presented at APS-2024 on a specific topic, please make use of the search by venue (APS-2024) service. To summarize the latest research published at APS-2024 on a specific topic, you can utilize the review by venue (APS-2024) service. To synthesizes the findings from APS 2024 into comprehensive reports, give a try to APS-2024 Research. If you are interested in browsing presentations by author, we have a comprehensive list of all APS-2024 authors & their presentations.
This curated list is created by the Paper Digest Team. Experience the cutting-edge capabilities of Paper Digest, an innovative AI-powered research platform that gets you the personalized and comprehensive updates on the latest research in your field. It also empowers you to read articles, write articles, get answers, conduct literature reviews and generate research reports.
Experience the full potential of our services today!
TABLE 1: Highlights of Data Science (GDS) Talks @ APS 2024 March Meeting
| Paper | Author(s) | |
|---|---|---|
| 1 | Advancements in The Autonomous Tuning of Semiconductor-based Qubits Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The progress we’ve made may offer a foundation for a new wave of explorations in automated qubit tuning and quantum computation research. |
Jonas Schuff ; Miguel Carballido ; David Craig ; Taras Patlatiuk ; Dominik Zumbuhl ; Natalia Ares; |
| 2 | Principled Approach to Automatically Annotating Charge Stability Diagrams Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: I will present a new, robust classical algorithm for fully automated labeling of two-dimensional (2D) charge stability diagrams of double-QD devices [3]. |
Justyna Zwolak ; Brian Weber ; Florian Luthi ; Felix Borjans; |
| 3 | Deep Reinforcement Learning for Robust Dynamical Decoupling Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Standard examples of dynamical decoupling protocols for qubit systems compose a train of pulsed control operations and periods of free evolution. We pose this problem in a reinforcement learning paradigm, by allowing a neural network agent to determine the choice of pulses for a spin system with dipolar interactions, magnetic disorder and control errors. |
George Witt ; Jner Tzern Oon ; Connor Hart ; Ronald Walsworth; |
| 4 | Fully Automated Coldstart Protocol for Semiconductor Quantum Dot Tune-up Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a combined algorithm for taking a double-dot device from cooldown to a desired charge state, including characterization and evaluation of device usability, and sensor and double quantum dot tuning. |
Torbjørn Rasmussen ; Anton Zubchenko ; Danielle Middlebrooks ; Lara Lausen ; Ferdinand Kuemmeth ; Justyna Zwolak ; Anasua Chatterjee; |
| 5 | Rapid Characterization of Spin Qubit Systems Using Open Source Resources Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we present an approach to address the rapid characterization challenges of NV centers in diamond through simplified instrumentation and optics based on open-source hardware and software. |
Daniel Mark ; Christopher Egerstrom ; Jonathan Marcks ; Jacob Feder ; Nazar Delegan ; Jiefei Zhang ; David Awschalom ; Paul Kairys ; F. Joseph Heremans; |
| 6 | Simulation-Driven Bayesian Hamiltonian Learning for Autonomous Characterization and Control of Spin-Defects Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we explore the full space of quantum controls and assess their utility in autonomous control and Hamiltonian learning tasks through explicit simulation of the underlying quantum dynamics incorporated into the learning process. |
Paul Kairys ; Jonathan Marcks ; Daniel Mark ; Christopher Egerstrom ; Nazar Delegan ; Jiefei Zhang ; David Awschalom ; F. Joseph Heremans; |
| 7 | Automated Tune-Up of Poor Man’s Majorana’s In A Two-Site Kitaev Chain Using A Neural Network Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we show that the predictions of a neural network, retrained on a small experimental data set, can be used to set gate voltages, which tune a two-site Kitaev chain into the sweet spot in realtime. |
David van Driel ; Rouven Koch ; Bas Ten Haaf ; Vincent Sietses ; Chunxiao Liu ; Michael Wimmer ; Eliska Greplova ; Srijit Goswami ; Jose Lado ; Leo Kouwenhoven; |
| 8 | Optimizing High-Fidelity Readout Circuit Using Reinforcement Learning Methods Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We seek to automate the tuning of high-fidelity readout and gate control in quantum dot (QD) systems using reinforcement learning. |
Harry Chalfin ; Tommy Boykin II ; Michael Stewart ; Michael Gullans ; Justyna Zwolak; |
| 9 | Feedback-based Calibration for Tuning and Drift Control of A Trapped-ion Quantum Processor Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Advanced control and readout hardware based on FPGAs can enable the low-latency feedback between qubit measurement results and pulse-level control necessary for real-time calibration and parameter tuning. In this talk, we introduce two low-latency calibration protocols which take advantage of these capabilities to update control parameters conditioned on the outcomes of simple quantum circuits. |
Nathan Miller ; Alicia Magann ; Robin Blume-Kohout ; Kevin Young; |
| 10 | Predicting The Electronic Structure of Matter at Scale with Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, I will present our recent advancements in utilizing machine learning to significantly enhance the efficiency of electronic structure calculations [1]. |
Attila Cangi; |
| 11 | Unsupervised Detection of Quantum Phases and Their Local Order Parameters from Projective Measurements Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we report designing a special convolutional neural network with adaptive kernels, which allows for fully interpretable and unsupervised detection of local order parameters out of spin configurations measured in arbitrary bases. |
Kacper Cybinski ; James Enouen ; Antoine Georges ; Anna Dawid; |
| 12 | Towards Learning The Disordered Hamiltonian with Graph Neural Networks from Experimental Snapshots Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we present a scalable approach to Hamiltonian learning with graph neural networks (GNNs). |
Anna Dawid ; Joseph Tindall ; Anirvan Sengupta ; Antoine Georges; |
| 13 | Enabling Analytics at Scale Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This talk will provide and overview of the internal tools, systems and approaches that we use to enable teams to perform analytics using our exabyte scale data warehouse. |
Alex Mellnik; |
| 14 | Analytics at Caterpillar Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This data can include time-series data, machine health alerts, fuel usage, GPS coordinates and operator-specific usage. In this presentation, we will describe how powered by this data, Caterpillar’s analytics can provide customers value at a lower cost of ownership, increased productivity and predictability, safety and reduced maintenance costs. |
Phillipe Tuckmantel; |
| 15 | Tough Decisions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The focus of this talk is about AI decision models my team creates that make complex, customer-focused, product development decisions in plant breeding. |
Adam Scott; |
| 16 | Applying A Physics Education to A Career As A Hedge Fund Data Scientist Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: I will discuss the skills required to become a successful data scientist, including those that can be learned on the job as well as several invaluable skills that are developed through scientific research. |
Christopher Reeg; |
| 17 | Predicting Aggregate Morphology of Sequence-defined Macromolecules with Recurrent Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, I will present the phase separation behavior of different sequences of a coarse-grained model for sequence defined macromolecules. |
Antonia Statt; |
| 18 | Active Learning for Discovering Complex Phase Diagrams with Gaussian Processes Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a Bayesian active learning algorithm that efficiently elucidates phase diagrams. |
Chunjing Jia ; Max Zhu ; Jian Yao ; Marcus Mynatt ; Hubert Pugzlys ; Shuyi Li ; Sergio Bacallado ; Qingyuan Zhao; |
| 19 | Data-driven Studies of Two-dimensional Materials and Their Nonlinear Optical Properties Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our research uses data-driven methods to investigate nonlinear optical (NLO) properties in van der Waals (vdW) materials. |
Kai Wagoner-Oshima ; Romakanta Bhattarai ; Trevor David Rhone; |
| 20 | Using Data to Enhance Mechanistic Modeling of Microstructure Evolution in Silicon Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, two examples of data-assisted mechanistic modeling are presented to illustrate how data may be used to ‘patch over’ modeling elements that are not fully specified. |
Talid Sinno; |
| 21 | Data-Driven Models for Predicting Stability of Electrocatalysts in Aqueous Environments Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we implemented a computational framework to identify the factors that define the stability of metal electrodes in aqueous environments. |
Seda Oturak ; Ismaila Dabo; |
| 22 | ChemChat | Conversational Expert Assistant in Material Science and Data Visualization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we present ChemChat, a web application and conversational assistant with a chatbot-driven user interface that is powered by non-GPT/OpenAI LLMs. |
Tim Erdmann ; Sarathkrishna Swaminathan ; Stefan Zecevic ; Brandi Ransom ; Nathan Park; |
| 23 | Towards A Multi-Objective Optimization of Subgroups for The Discovery of Materials with Exceptional Performance Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The subgroup-discovery (SGD) approach identifies local rules describing exceptional subsets of data with respect to a given target. |
Lucas Foppa ; Matthias Scheffler; |
| 24 | Equivarient Electron Density Predictions Accelerate Density Functional Theory Calculations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We develop an E(3)-equivarient deep learning model to predict the self-consistent, ground-state electron density that outperform other models found in the literature such as DeepDFT for organic molecules and inorganic materials. |
Thomas Koker ; Keegan Quigley ; Eric Taw ; Lin Li; |
| 25 | Generative Neural Networks for Synthetic PBX Microstructures with Varying Levels of Damage to Evaluate Shock Sensitivity Through Meso-scale Simulations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we present HEDS (Heterogeneous Energetic Damage Simulator), a versatile tool designed for generating varying levels of damage within microstructure images of a specific plastic bonded explosive (PBX). |
Irene Fang; |
| 26 | Recent Advancements in SISSO As Applied to Thermal Conductivity Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we present new concepts for the feature creation step that introduce basic grammatical rules for the generated expressions. |
Thomas Purcell ; Matthias Scheffler; |
| 27 | Closed-Loop Control of Non-Newtonian Fluid Flow Using Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this research, we introduce a novel methodology that amalgamates electrical flow monitoring with machine learning to meticulously control non-Newtonian fluid flow. |
Xin Zhang ; Huilu Bao ; Xiaoyu Zhang ; Xiao Fan ; Jinglei Ping; |
| 28 | Limitations of Noisy Quantum Devices in Computational and Entangling Power Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: For computation with general classical processing, we show that noisy quantum devices with a circuit depth of more than O(log (n)) provide no advantages in any quantum algorithms for decision problems. |
Yuxuan Yan ; Zhenyu Du ; Junjie Chen ; Xiongfeng Ma; |
| 29 | Reservoir Computing for Efficient Decoding of Error Syndromes in Surface Code Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we propose a decoder using a reservoir computer (RC). |
Azarakhsh Jalalvand ; Leon Bello ; Supantho Rakshit ; Benjamin Lienhard ; Egemen Kolemen ; Hakan Tureci; |
| 30 | Efficient Separate Quantification of State Preparation Errors and Measurement Errors on Quantum Computers and Their Mitigation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Rev. A 106, 012439 (2022)], we propose a simple and resource-efficient approach to quantify separately the state preparation and readout error rates. |
Hongye Yu ; Tzu-Chieh Wei; |
| 31 | Shallow Unitary Decompositions of Quantum Fredkin and Toffoli Gates for Connectivity-aware Equivalent Circuit Averaging Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we will describe how we applied our automated method to decompose Fredkin and Toffoli gates under all-to-all and linear qubit connectivities, the latter with two different routings for control and target qubits. |
Pedro Cruz ; Bruno Murta; |
| 32 | Noise-Robust Error Mitigation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a certain cost function that guides us towards mitigating the effects of the noise prior to fitting the noisy data. |
Amin Hosseinkhani ; Alessio Calzona ; Tianhan Liu ; Adrian Auer ; Inés de Vega; |
| 33 | Continuous Variable Quantum Boltzmann Machine Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we propose a CV QBM that utilizes previously developed CV quantum neural network that defines quantum circuit for Gibbs state preparation and the parameters to be trained. |
Kubra Yeter Aydeniz ; George Siopsis ; Shikha Bangar ; Leanto Sunny; |
| 34 | Genesis of Quantum Supremacy of Atomic Boson Sampling Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In conclusion, the analysis of the box BEC trap reveals genesis of quantum supremacy of atomic boson sampling over classical computing. |
Vitaly Kocharovsky; |
| 35 | Revolutionizing Computations: Quantum Circuit Analogues with Nonlinear Acoustic Waves Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we introduce a paradigm utilizing logical phi-bits, classical analogues of qubits using nonlinear acoustic waves, supported by an externally driven acoustic metastructure. |
M Arif Hasan ; Pierre Deymier ; Keith Runge ; Josh Levine; |
| 36 | Free Energy, Conformationa Dynamics and Simulations of Nanocrystals with Explicit Ligands Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk I will present different algorithms and methods to compute thermodynamic and dynamical quantities when NC are modeled with explicit ligands, mostly through all atom or united models, but time permitting, some discussion will be included for coarse-grained systems. |
Alex Travesset; |
| 37 | Evaluating Approaches for On-the-fly Machine-learning Interatomic Potentials for Activated Mechanisms Sampling with ARTn Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we evaluate the benefits of using specific versus general on-the-fly machine-learning potentials for the study of activated mechanisms. |
Eugene Sanscartier ; Normand Mousseau; |
| 38 | Development of MLIP to Model Corrosion Behavior in Molten Salt Reactors Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we developed and evaluated the efficacy of Machine Learning Interatomic Potentials (MLIP) designed for Molten Salt and its relevance toward the corrosion behavior. |
Matthew Bruenning ; Ridwan Sakidja; |
| 39 | Machine Learning Assisted Design of Effective Potentials, Surface Ligand Patterns, and Annealing Protocols for Colloidal Self-assembly Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we will demonstrate how machine learning can speed up both the exploration and the targeted design efforts in colloidal assembly. |
Gaurav Arya ; Yilong Zhou ; Po-An Lin ; Safak Callioglu ; Sigbjorn Bore ; Simiao Ren ; Yunqi Yang ; Andrea Tao ; Leslie Collins ; Francesco Paesani ; Yonggang Ke ; Stefan Zauscher; |
| 40 | How to Use Stochastic Devices in Probabilistic Calculations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Switching from software-defined random number generators to specialized stochastic devices may not only make the computationally expensive process of sampling cheaper, but can motivate the formulation of more complex approaches that shift additional burden away from traditional computation and towards sampling. This talk focuses on establishing figures of merit for stochastic devices which are derived from the quality of the samples they produce. |
Shashank Misra ; Christopher Allemang ; Christopher Arose ; Brady Taylor ; Andre Dubovskiy ; Ahmed Sidi El Valli ; Laura Rehm ; Andrew Haas ; Andrew Kent ; Leslie Bland ; Suma Cardwell ; Darby Smith ; James Aimone; |
| 41 | First-principles Machine-learning Quantum Dynamics at 0K in SrTiO3: Light-induced Ultrafast Ferroelectric Transition Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we develop a novel technique, the time-dependent self-consistent harmonic approximation (TDSCHA [1]), and use it to simulate the quantum dynamics in SrTiO 3 at 0K. |
Francesco Libbi ; Lorenzo Monacelli ; Anders Johansson ; Boris Kozinsky; |
| 42 | Diverse Training Data Generation for Machine-learning Interatomic Potentials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we present a generalization of a previously developed method based on the automated maximization of the information entropy of the descriptor distribution. |
Aparna P. A. Subramanyam ; Danny Perez; |
| 43 | A Machine Learning Interatomic Potential for Ge-Te Alloys Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an interatomic potential for GeTe alloys based on the recent atomic cluster expansion (ACE) architecture, trained with representative configurations from DFT calculations spanning the entirety of the Ge xTe 1-x system. |
Tom Arbaugh ; Owen Dunton ; Francis Starr; |
| 44 | Machine Learned Force and Torque Predictions for Molecular Dynamics of Non-spherical Colloids Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we have trained neural nets that take the pair configuration as input and give the forces and torques between the two rigid bodies (cylinders and cubes) as output. |
Bahadir Rusen Argun ; Antonia Statt; |
| 45 | Machine Learning Models for Partition Functions: Predicting Thermodynamic Properties and Exploring Transition Pathways Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The results of these simulations were then combined into datasets that allowed us to train and validate ML models. We used these models to build artificial neural networks capable of predicting partition functions for a wide range of conditions. |
Caroline Desgranges ; Jerome Delhommelle; |
| 46 | Controlling Colloidal Assembly & Reconfiguration Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We demonstrate real-time control of colloidal assembly and reconfiguration for a variety of colloidal particle shapes and states including hierarchical microstructures. |
Michael Bevan; |
| 47 | Quantifying Dynamics of Soft and Active Matter with Microscopy and Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Differential dynamic microscopy (DDM) offers a powerful technique to quantify the dynamics, combining principles from optical microscopy and light scattering. |
Gildardo Martinez ; Justin Siu ; Dylan Gage ; Emma Kao ; Juan Carlos Avila ; Ruilin You ; Ryan McGorty; |
| 48 | Learning Active Nematohydrodynamics with SINDy-PI Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, I will describe the application of SINDy-PI to identify a hydrodynamic theory for dry active nematics, meaning that long-range hydrodynamic interactions are negligible, such as in cell sheets or dense active nematics on a frictional substrate. |
Chris Amey ; Michael Hagan ; Aparna Baskaran; |
| 49 | Grant Rotskoff Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: I will describe a theoretical framework for controlling the response and dynamics of nonequilibrium systems using time-dependent external couplings. |
Grant Rotskoff; |
| 50 | Learning Cell Division Strategies Across Diverse Organisms Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, understanding the governing rules of cell growth and division within a dynamical systems framework remains a challenge. To address this challenge, we model the cell-size dynamics using a stochastic differential equation (SDE) with a Poisson process describing cell division events. |
Shijie Zhang ; Chenyi Fei ; Jorn Dunkel; |
| 51 | A Spectral Approach for Learning Spatiotemporal Neural Differential Equations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we will introduce a novel neural-ODE based method that uses spectral expansions in space to learn spatiotemporal DEs. |
Mingtao Xia ; Xiangting Li ; Qijing Shen ; Tom Chou; |
| 52 | Controlling Assembly and Encoding in Active Matter Using Light Patterns Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose protocols to control smart templated assembly and motion in active matter and identify a metric to quantify the amount of information encoded in the active fluid post-application of the light pattern. |
Jerome Delhommelle ; Caroline Desgranges; |
| 53 | Improved KCNQ2 Gene Missense Variant Interpretation with Artificial Intelligence Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We found that combining primate genome information, readily available features, such as AlphaFold structural information, allele frequency index, residue conservation and other commonly used protein descriptors, provides foundations to build reliable gene-specific machine learning models. We present transferable methodology able to accurately classify KCNQ2 missense variants with sensitivity and specificity scores above 97%. |
Aritz Leonardo ; Aitor Bergara ; Alvaro Villarroel ; Markel García Ibarluzea ; Rafael Ramis Cortés ; Alba Sáez-Matía ; Eider Núñez; |
| 54 | Uncovering Interpretable Low-dimensional Geometric Structures in Gene Expression Using Curvature Regularized Variational Autoencoders Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, these embeddings often rely on preserving similarities between data points such that the learned manifold exists in data-similarity space, making it difficult to interpret, interrogate, and generalize the manifold in the natural coordinates of neurons and genes. Here, we develop tools from variational inference—the variational autoencoder (VAE)—that learns an explicitly geometric and nonlinear manifold in these natural coordinates. |
Jason Kim ; Nicolas Perrin-Gilbert ; Paul Klein ; Erkan Narmanli ; Chris Myers ; Itai Cohen ; Joshua Waterfall ; James Sethna; |
| 55 | Convolutional Neural Network Analysis of Molecular Docking for Cancer Drug Discovery Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we performed a comparative study of series of convolutional neural networks (CNN) including search-based methods such as GNINA and a diffusion generative model (DiffDock) approach to optimize the drug design process for Mouse Double Minute 2 (MDM2) proteins. |
Gaige Riggs ; Ridwan Sakidja; |
| 56 | Combining Neural Networks and Principal Component Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Several results regarding the rate of convergence and accuracy of neural network calculations supplemented by principal component analysis are presented and discussed. These … |
David Yevick ; Karolina Suszek; |
| 57 | Representation Learning for Data-driven Analysis of Soft Matter Simulations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, I will present my work in unsupervised machine learning to characterize local and global ordering in soft matter systems. |
Wesley Reinhart; |
| 58 | Exploiting Invariant Manifolds for Optimal Control in Active Hydrodynamic Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: For active nematic channel flow, we obtain a reduced-order representation of the phase space in terms of a directed graph, in which ECS are nodes, and dynamical connections are edges. |
Piyush Grover ; Michael Norton ; Caleb Wagner ; Rumayel Pallock ; Jae Sung Park; |
| 59 | Leveraging Multi-task Model for Improving Mechanical Property Predictions of High Entropy Alloys (HEAs) Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, the correlation between property, chemistry, and processing can potentially be leveraged using methods like multi-task learning (MTL). Therefore, we will compare a MTL model vs single task models on some HEA mechanical properties. |
Arindam Debnath ; Wesley Reinhart; |
| 60 | INTERSECT: The Interconnected Science Ecosystem Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While this is a grand and noble goal, it is also abstract. In this talk I will outline efforts to make such an abstract vision a reality. |
Robert Moore; |
| 61 | Performance-Portable Implementation of SISSO++ and Its Application in Materials’ Mobility Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we present an updated implementation that uses the C++ performance-portability framework Kokkos [4] to offload the performance-critical regions of the algorithm to accelerators, such as Nvidia or AMD GPUs. |
Yi Yao ; Sebastian Eibl ; Markus Rampp ; Luca Ghiringhelli ; Thomas Purcell ; Matthias Scheffler; |
| 62 | Bridge The Gap Between Industrial Data and Large Language Model (LLM) By Mimicking The Brain Hemispheres Function and Thought Process of An Industrial Data Scientist Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Instead of costly fine-tuning approach, this abstract presents an innovative approach to bridge the gap between industrial data and LLMs using technologies like named entity recognition, retrieval augmented generation and Knowledge Graphs (KG). By mimicking the brain hemispheres functions (fact-based analysis & reasoning vs. intuitive & holistic thinking) and thought process (balance and trade-off) of an industrial data scientist, we aim to optimize LLM based applications for industrial data analysis, enabling them to effectively understand and generate insights from complex datasets. |
Jian Yang ; Michael Dessauer ; Gregory Parkison ; Constantyn Chalitsios; |
| 63 | Understanding Attention in The Mean-field Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: One avenue to tackle this problem is to understand how the geometry of the token vectors changes as they propagate deeper and deeper into the network. We analyze this recursion by means of a replica-symmetric ansatz which gives a starting point for perturbation theory. |
Aditya Cowsik ; Surya Ganguli ; Tamra Nebabu ; Xiao-Liang Qi; |
| 64 | Implementation of An Optimally Windowed Chirp Method for Industrial Rheological Measurements Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk we will discuss the successful implementation of this methodology into an industrial analytical R&D framework, using commercially available rheometers. |
Alessandro Perego ; Damien Vadillo ; Alex Bourque ; Matthew Mills ; Grace Kemer ; Aaron Hedegaard ; Mitch Rock ; Ross Behling; |
| 65 | Crystal Hypergraph Convolutional Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Such constructions restrict representations to atom and pair-wise descriptions or features that are updated via messages composed of origin and neighboring atom features, as well as the corresponding ‘bond’ features. In this talk, we propose a natural extension of such frameworks, which employs the use of hypergraphs to generalize to higher-order geometrical structures (such as triplets and motifs) within the same mathematical representation of the crystal. |
Alexander Heilman ; Weiyi Gong ; Qimin Yan; |
| 66 | Physics-Informed Machine Learning for Addressing Challenges in Static and Time-Dependent Density Functional Theory Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We explore the potential of Physics-Informed Machine Learning (ML) in addressing key computational tasks in both static and time-dependent Density Functional Theory (DFT/TDDFT). The talk will focus on two projects that employ advanced ML techniques, specifically Physics-Informed Neural Networks (PINNs) and Fourier Neural Operators (FNOs), to tackle these complex tasks. |
Karan Shah ; Attila Cangi; |
| 67 | Equivariant Symmetry Breaking Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we propose the idea of symmetry breaking sets (SBS). |
YuQing Xie ; Tess Smidt; |
| 68 | Multistability Towards Reprogrammable Mechanical Devices Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Notably, the multi-welled energy landscape of the linkages can be easily modified through geometry adjustments triggered by environmental energy inputs, enabling autonomous adaptation. As a practical demonstration of this platform, we create a four-degree-of-freedom robot capable of navigating mazes and avoiding obstacles — all without the need for computational intelligence and utilizing only a single actuator. |
Leon Kamp ; Katia Bertoldi; |
| 69 | Identifying Traces of Learning in Physical Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Functionality in these systems emerges from a dual optimization: a simultaneous minimization in a learning and a physical landscape. Here we study this interplay within functional linear resistor networks, a paradigmatic model for physical learning systems. |
Marcelo Guzmán ; Felipe Martins ; Andrea Liu; |
| 70 | Neural Computation Without Neurons Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our work suggests that exploiting ubiquitous physical phenomena, such as nucleation, is an underexplored powerful route to neural computation without neurons. |
Arvind Murugan; |
| 71 | Physics for Neuromorphic Computing Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We have performed simulations and experiments to demonstrate quantum neuromorphic computing with superconducting circuits. |
Danijela Markovic; |
| 72 | Physical Neural Networks Trained with A Physics-aware Backpropagation Algorithm Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Using a version of backpropagation suited to experimental physical systems, we have demonstrated physical neural networks based on nonlinear optics, analog electronics, mechanics, and coupled oscillators [Wright, Onodera et al., Nature (2022)]. In this talk, I will review this and our recent work on physical neural networks, primarily with optical systems. |
Logan Wright; |
| 73 | The Physical Effects of Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In earlier work, we established a framework for deriving local learning rules for a broad class of physical networks, including some inspired by biological systems, and demonstrated that these rules are physically realizable through laboratory experiments. Here I will describe how learning induces architectural changes in the physical network and a remodeling of its energy landscape, leading to a decrease in the effective physical dimension and a realignment of low eigenvectors of the energy Hessian with the learned task. |
Menachem Stern; |
| 74 | Spatial Signatures of Learning in Self-Learning Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We build on [1,2] and use the low eigenmodes of the physical Hessian to build an understanding of how self-learning electrical circuits learn various machine-learning tasks. |
Felipe Martins ; Marcelo Guzman ; Andrea Liu; |
| 75 | Physical Learning Using Mechanical Spring Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In our work, we present a novel method harnessing adjoint variable methods to derive a mechanical analogue of backpropagation to facilitate highly efficient training of spring networks. |
Shuaifeng Li ; Xiaoming Mao; |
| 76 | Memory-induced Long-range Order in Dynamical Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Time non-locality, or memory, is a nonequilibrium property of a physical system characterized by perturbations to the system at one time affecting the system’s state at a later time. In this talk, we show that such a property induces spatial long-range order even if the system’s units are coupled locally. |
Chesson Sipling ; Massimiliano Di Ventra; |
| 77 | Dynamic Third-party Entrainment and Learning in Systems of Multistable Oscillators Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we propose a generalization of the learning rule for pairs of oscillators to model learning among an arbitrary number of multistable HKB oscillators and demonstrate how multi-oscillator coupling influences the learning dynamics of oscillator pairs. |
Joseph McKinley ; Mengsen Zhang ; Alice Wead ; Christine Williams ; Emmanuelle Tognoli ; Christopher Beetle; |
| 78 | Collective Dynamics and Memory-induced Long-range Order in Spiking Oscillator Arrays Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we show large-scale simulations of the dynamics of both 1D and 2D arrays of thermally coupled neuristors. |
Yuan-Hang Zhang ; Chesson Sipling ; Massimiliano Di Ventra; |
| 79 | Precise Dynamical Steady States in Disordered Materials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The goal of this work is to study the feasibility of creating disordered materials with exotic properties in the dynamic regime. |
Marc Berneman ; Daniel Hexner; |
| 80 | Flashpoints Signal Hidden Inherent Instabilities in Land-Use Planning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we show that optimization-based planning approaches with generic planning criteria generate a series of unstable "flashpoints" whereby tiny changes in planning priorities produce large-scale changes in the amount of land use by type. We give quantitative arguments that the flashpoints we uncover in MOLA models are examples of a more general family of instabilities that occur whenever planning accounts for factors that coordinate use on- and between-sites, regardless of whether these planning factors are formulated explicitly or implicitly. |
Greg Van Anders ; Hazhir Aliahmadi ; Maeve Beckett ; Sam Connolly ; Dongmei Chen; |
| 81 | Acceleration in Optimization Using Bayesian Optimization for Broad Permutation Space Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: As a first step, we focused on the take-off or landing aircraft management and formulated it as a permutation-space optimization problem. |
Tomohisa Okada ; Nobuyuki Yoshikawa ; Masayuki Ohzeki; |
| 82 | Trainable and Resettable Nitinol-composites Metamaterials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We create building blocks for adaptable and resettable metamaterials by embedding nitinol wires within silicone rubber springs. |
Paul Baconnier ; Martin van Hecke; |
| 83 | Shape-controllable Non-reciprocal Robotic Metamaterial Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we adapt the contrastive learning protocol to an active system, our non-reciprocal robotic metamaterial, and show that it can actively learn and generate desired complex shapes. |
Yao Du ; Jonas Veenstra ; Ryan van Mastrigt ; Corentin Coulais; |
| 84 | Ab Initio-driven Machine-learning Models for Aqueous Systems, Interfaces, and Molten Salts Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In particular, we take advantage of the Deep Potential (DeePMD) methodology to capture energies and forces in a given system, as determined from quantum density functional theory. |
Athanassios Panagiotopoulos; |
| 85 | Machine Learning for Molecular and Materials Science Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We will present new extensions such as charged systems, scailng to miilions of atoms and hundreds of GPUS, and to the calculations of other properties such as dipoles, NMR chemical shifts, IR spectra, etc. |
Adrian Roitberg; |
| 86 | Self-assembly of Electronic Materials and The Power of Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Solution processing offers a low-energy-use and deceptively simple protocol to create electronically active thin films with high solar cell efficiency. In this talk, we will cover our accomplishments, challenges and outlook for what Bayesian optimization might achieve to help us understand, and hence control, these processes. |
Paulette Clancy; |
| 87 | Exploration of New High-Entropy Materials Enabled By Quantum Computing Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we will explore emerging quantum computing technologies, encompassing quantum simulators and hardware, to effectively address the complex task of elemental design and contribute to the discovery of novel HEMs. |
Houlong Zhuang ; Payden Brown; |
| 88 | Mary Jo Ondrechen Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Machine Learning for protein function prediction and for understanding how enzymes work Our Machine Learning methodology, Partial Order Optimum Likelihood (POOL) is used to … |
Mary Jo Ondrechen ; Lakindu Pathira Kankanamge ; Atif Shafique ; Suhasini Iyengar ; Kelly Barnsley ; Penny Beuning; |
| 89 | Combining Data, Physics and Machine Learning for Accelerating Materials Computations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We pursue a multi-tier method development strategy in which machine learning algorithms are combined with exact physical symmetries and constraints to significantly accelerate computations of electronic structure and atomistic dynamics. |
Boris Kozinsky; |
| 90 | Performing Hartree-Fock Many-body Physics Calculations with Large Language Models Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: In the last few years, large language models (LLMs) have exhibited an unprecedented ability to perform complex linguistic and reasoning tasks. To date, evaluation of scientific … |
Eun-Ah Kim ; Haining Pan ; Nayantara Mudur ; William Taranto ; Subhashini Venugopalan ; Yasaman Bahri ; Michael Brenner; |
| 91 | Towards Open Science in Materials Synthesis and Characterization: Experiences from The 2DCC Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Part of this mandate extends to making the expertise and data developed by the 2DCC accessible, with synthesis recipes and characterization data to be made publicly available after publication of results as registered dataset DOIs. This talk discusses the efforts and challenges of implementing this vision across groups in a university setting, where the data and processes at every level from growth, to fabrication, and characterization need to be captured from a host of various instruments, along with the metadata necessary to make them interpretable. |
Anthony Richardella ; Konrad Hilse ; Kevin Dressler ; Wesley Reinhart ; Joan Redwing ; Nitin Samarth ; Vincent Crespi; |
| 92 | Complex Langevin and Machine Learning Approaches to The Non-linear Sigma Model with A Topological Term Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work investigates the phase transitions of disordered quantum materials via the nonlinear sigma model with a finite topological term—which contains a complex term—using two methods: complex Langevin and unsupervised learning. |
Casey Berger ; Adelaide Esseln; |
| 93 | Machine Learning of Quantum Walk with Classical Randomness Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We implement three manual methods based on the distribution, moment of inertia, and inverse participation ratio, and three supervised machine-learning methods, including the support vector machine (SVM), multi-layer perceptron neural network, and convolutional neural network, to locate the transition point. |
Christopher Mastandrea ; Chih-Chun Chien; |
| 94 | Machine Learning Discovery of A New Descriptor for Topological Semimetal Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: For this, a reliable measurement based and expertly curated data and bench marking insight by expert researcher are critical. As a first step towards such program, we focus on the topological semi metal (TSM) among square-net materials as target property, inspired by the expert identified descriptor based on structural information: the tolerance factor [1]. |
YANJUN LIU ; Krishnanand Mallayya ; Milena Jovanovic ; Wesley Maddox ; Andrew Wilson ; Sebastian Klemenz ; Leslie Schoop ; Eun-Ah Kim; |
| 95 | Variational Formulation of Physics-informed Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a variational PINN (vPINN) algorithm that optimizes functionals in integral form (e.g., Lagrangian, Hamiltonian, or Rayleighian) to overcome the aforementioned disadvantages: vPINN naturally involves lower-order derivatives and replaces the ad hoc weight factors with rigorous physical scales. |
Chinmay Katke ; C. Nadir Kaplan; |
| 96 | A Data-driven Framework for Non-stationary Complex Systems: Blending Generalized Langevin and Neural Ordinary-differential Equations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Existing mathematical models pose considerable challenges, e.g. requiring a priori understanding of the prevailing dynamics of the CS at hand which, in turn, limits their applicability, especially when the CS alternates between stationary and non-stationary behavior. We propose here a general framework for CSs which addresses these challenges. |
Antonio Malpica-Morales ; Serafim Kalliadasis ; Miguel Duran-Olivencia; |
| 97 | Machine Learning for Adsorption Processes Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Machine Learning for Adsorption Processes – This talk will discuss application of various machine learning approaches that can aid in the discovery of porous materials for gas storage and in the optimization of process conditions for chemical separations. |
J. Ilja Siepmann; |
| 98 | Optimization of Physical Quantities in The Autoencoder Latent Space Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a strategy for optimizing physical quantities based on exploring in the latent space of a variational autoencoder (VAE). |
Seong Min Park ; Changyeon Won ; Han Gyu Yoon ; Doo Bong Lee ; Jun Woo Choi ; Hee Young Kwon; |
| 99 | Crystal Structure Generative Modeling Based on Diffusion Probabilistic Models and Variational Autoencoder Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our work shows a promising data-driven scheme of crystal structure generation that can well approximate true ground-state configurations. |
Teerachote Pakornchote ; Natthaphon Choomphon-anomakhun ; Sorrjit Arrerut ; Chayanon Atthapak ; Sakarn Khamkaeo ; Thiparat Chotibut ; Thiti Bovornratanaraks; |
| 100 | Grokking and Emergent Capabilities in Deep Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This effect is known under the names of "emergent capabilities" and "grokking". In this talk I will describe a few simple models based on neural networks learning simple mathematical operations that elucidate this behavior. |
Andrey Gromov; |
| 101 | Average-Reward Reinforcement Learning Using Insights from Non-Equilibrium Statistical Mechanics Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Although this framework has the benefit that it leads to useful bounds and convergence properties, it is not appropriate for problems in which discounting is not a principled approach. To address this issue, we consider an alternative framework based on the average-reward formalism, which optimizes for long-term average returns. |
Jacob Adamczyk ; Argenis Arriojas Maldonado ; Stas Tiomkin ; Rahul Kulkarni; |
| 102 | To Grok or Not to Grok: Disentangling Generalization and Memorization on Corrupted Algorithmic Datasets Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Robust generalization is a major challenge in deep learning — it is often very difficult to know if the network has memorized a particular set of examples or understood the underlying rule (or both). Motivated by this challenge, we study a simple and interpretable model where generalizing representations are understood analytically, and are easily distinguishable from the memorizing ones. |
Darshil Doshi ; Aritra Das ; Tianyu He ; Andrey Gromov; |
| 103 | Generalization Error in The Spherical Perceptron Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Notably, we find that this phenomenon only occurs when the system experiences a jamming transition that maintains replica symmetry. We present numerical and theoretical evidence supporting this observation. |
Gilhan Kim ; Yongjoo Baek ; Hyungjoon Soh; |
| 104 | Criticality from The Functional Development of A Learning Machine Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Instead of tracing out microscopic details of the neural networks that produce specific functionality, we aim for a macroscopic understanding of the evolution and transitions of the collective states of the neural systems leading to the fulfillment of the required functions. |
Ting-Kuo Lee; |
| 105 | Training Machine Learning Emulators to Preserve Invariant Measures of Chaotic Attractors Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose an alternative framework designed to preserve invariant measures of chaotic attractors that characterize the time-invariant statistical properties of the dynamics. |
Peter Lu ; Ruoxi Jiang ; Elena Orlova ; Rebecca Willett; |
| 106 | Statistical Mechanics of Dynamical System Identification Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we formulate system identification as a two-level Bayesian inference problem that explicitly separates variable selection from variable values and uses statistical mechanics techniques to compute the posterior parameter distribution in closed form and avoid Monte Carlo sampling. |
Andrei Klishin ; Joseph Bakarji ; J. Nathan Kutz ; Krithika Manohar; |
| 107 | Effective Dynamics of Generative Adversarial Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we present a simplified model of GAN training dynamics, which allows us to study the conditions under which mode collapse occurs. |
Shenshen Wang ; Steven Durr ; Youssef Mroueh ; Yuhai Tu; |
| 108 | Machine Learning That Predicts Well May Not Learn The Correct Physical Descriptions of Glassy Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a simple model for the rearrangement process and study the ability of SVM to learn the known activation energy in this model. |
Arabind Swain ; Sean Ridout ; Ilya Nemenman; |
| 109 | Tracking Parameter Variations in Nonlinear Dynamical Systems Using Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Formulating an inverse problem and exploiting the machine learning scheme of reservoir computing, we develop a model-free and fully data-driven framework to accurately track time-varying parameters from partial state observation in real time. |
Zheng-Meng Zhai ; Mohammadamin Moradi ; Ying-Cheng Lai; |
| 110 | Sparse Spectra in Learned Representations of Symmetries Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The learned representation is a discrete Fourier encoding of the input and output integers, but curiously it uses only a sparse subset of the possible frequencies. Here we show that some much simpler networks reproduce this sparse behaviour, allowing a more detailed analytic understanding. |
Michael Abbott ; Benjamin Machta; |
| 111 | Dynamics of Representational Learning in Brain and Artificial Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we will discuss the commonalities and differences between learning dynamics of realistic neural networks and artificial neural networks in the context of representational learning by using two examples from the mammalian olfactory system: 1) representational drift in piriform cortex; 2) alignment of neural representations from two sides of the brain. |
Yuhai Tu ; Guillermo Barrios Morales ; Miguel Muñoz ; Bo Liu ; Venketash Murthy ; Shanshan Qin; |
| 112 | What Does A Neuron Do? A New Model for Neuroscience and AI Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we present an alternative viewpoint, casting neurons as feedback controllers in closed loops comprising fellow neurons and the external environment. |
Dmitri Chklovskii; |
| 113 | A Statistical Theory of Inferring Population Geometry from Large-Scale Neural Recordings Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: As we add more neurons, are we recording enough trials in order to infer the population geometry of neural activity? We derive new theories, based on random matrices and free probability, to answer this question, comparing the predictions made in two distinct regimes: an extensive limit where the dimensionality of data is proportional to the number of recorded neurons and trials, and an intensive limit where the dimensionality is finite. |
Itamar Landau; |
| 114 | Hyperbolic Geometry and Information Acquisition in Biological Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: I will describe how the use of hyperbolic geometry can be helpful for visualizing and analyzing information acquisition and learning process from across biology, from viruses, to plants and animals, including the brain. |
Tatyana Sharpee; |
| 115 | Signatures of Abstraction Learning in Primates Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: How are these models represented in the dynamics of brain activity? We approach this question through the exploration of schema formation in nonhuman primates. |
Adrienne Fairhall; |
| 116 | Walking The Surfaces with AI-powered MD Simulations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In all these applications, it is crucial to understand the behavior of these peptides/enzymes as a function of their sequences (i.e., composition) and solution conditions such as temperature, pressure, additives, and surfaces. In our work, we explore these aspects using molecular simulations. |
Sapna Sarupria ; Varun Gopal ; Salman Bin Kashif; |
| 117 | Enhanced Sampling Using Birth-Death Algorithm Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, when walkers become correlated, it becomes crucial to implement a population control strategy to enhance their performance. In this talk, we introduce one such population control scheme for running multiple walkers in parallel, where we enhance the molecular sampling strategy by augmenting with a birth/death process 1. |
ARCHANA GOPAKUMAR REMANIDEVI ; Benjamin Pampel ; Simon Holbach ; Lisa Hartung ; Omar Valsson ; Burkhard Dunweg; |
| 118 | Stochastic Resetting for Enhanced Sampling Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a new approach for enhanced sampling of Molecular Dynamics (MD) simulations using stochastic resetting (SR). |
Ofir Blumer ; Shlomi Reuveni ; Barak Hirshberg; |
| 119 | Manifold Learning of Collective Variables for Enhanced Sampling Simulations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we present a manifold learning method called multiscale reweighted stochastic embedding (MRSE) for automatically constructing CVs to represent and drive the sampling of free energy landscapes in enhanced sampling simulations. |
Omar Valsson; |
| 120 | Efficient Sampling for Structure Search Using VAE-Organized Latent Spaces and Genetic Algorithms Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we will discuss the performance of the generative and evolutionary synergistic framework based on the tests performed on the CdTe system using force fields and the IrOx system using DFT calculations. |
Venkata Surya Chaitanya Kolluru ; Nina Andrejevic ; Maria Chan; |
| 121 | Complex Local Environments Classification of Shape Particles Through Shape-symmetry Encoded Data Augmentation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our work thus presents a valuable tool for investigating self-assembly processes on shape particles, with potential applications in structure identification of molecular or coarse-grained systems. |
Shih Kuang Lee ; Sharon Glotzer ; Sun-Ting Tsai; |
| 122 | Learning All-atom Molecular Reactions Using Data-driven Approaches Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we describe how simulations of liquid structure and dynamics of organic molecules undergoing thermal decomposition reactions can be achieved using hybrid DFT, active learning [1], and machine learning force fields [2]. |
Julia Yang ; Whai Shin Amanda Ooi ; Zachary Goodwin ; Yu Xie ; Ah-Hyung Alissa Park ; Boris Kozinsky; |
| 123 | Exploring Transferability of Machine Learning Interatomic Potentials for Reactive Chemistry Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, just like other machine learning models, MLIP faces challenges when it comes to transferability, specifically to systems of chemical space beyond its training. Here we explore sampling techniques that can allow MLIP such as ANI and NequIP to obtain transferability beyond its training data to achieve accurate bond dissociation across chemical space. |
Quin Hu ; Jason Goodpaster; |
| 124 | Active Learning of Diffusion Pathways for Machine-Learned Interatomic Potentials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To that end, we present a workflow that includes different diffusion pathway sampling strategies used in conjunction with active learning to generate MLIP training data for kinetic modelling. |
Michael Waters ; James Rondinelli; |
| 125 | Modeling Reaction-diffusion in The Liquid-phase Heterogeneous Catalysis Using Machine-learned Force Field Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this presentation, we will share our recent endeavors in modeling liquid-phase reactions catalyzed by zeolites, shedding light on our achievements and challenges. |
Neeraj Rai ; Woodrow Wilson; |
| 126 | Charge-dependent Atomic Cluster Expansions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Using newly developed charge-dependent atomic cluster expansion (ACE) descriptors and shadow molecular dynamics-inspired charge relaxation schemes, we help address some of these challenges with charge-dependent ML-IAPs. In this work, we explore the benefits of using charge-dependent ACE ML-IAPs and how they can help correct spurious behavior typically encountered in dynamic-charge molecular dynamics simulations. |
James Goff; |
| 127 | Rapidly Converging Cluster Expansions By Transfer Learning from Empirical Potentials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Despite considerable advances in CE methodologies [1], there remain challenges associated with the sampling of lattice configurations when applied to systems with low symmetry or a high number of chemical components ( e.g., high-entropy alloys). In this work, we address these challenges by employing active learning to reduce the number of first-principles calculations in a large training set. |
Amirreza Dana ; Ismaila Dabo ; Susan Sinnott ; Lingxiao Mu; |
| 128 | Accelerated Predictions of Charge Density Evolution in MD Simulations Using Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In our study, we compare two versatile model architectures – Feed Forward Neural Networks (FFNN) and Long Short Term Memory (LSTM) networks in terms of their accuracy in forecasting the atomic charge density. |
Aditya Venkatraman ; Mark Wilson ; David Montes de Oca Zapiain; |
| 129 | Scaling Laws and Emergent Behaviors in Foundation Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We investigate both an "open-box" approach, when the access to learning dynamics and internal metrics of a neural network are available (e.g., in the case of "grokking" behavior), as well as "closed-box" approach where the predictions of future behavior must be made solely based on the previous behavior, without internal measurements of the system being available. |
Irina Rish; |
| 130 | Reliable Emulation of Complex Functionals By Active Learning with Error Control Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Conventional "space-filling” designs, including random sampling and Latin hypercube sampling, become inefficient as the dimensionality of the input variables increases, and the predictive accuracy of the emulator can degrade substantially for a test input away from the training input set. To address this fundamental challenge, we develop a reliable emulator for predicting complex functionals by active learning with error control (ALEC). |
Xinyi Fang ; Mengyang Gu ; Jianzhong Wu; |
| 131 | Towards Measuring Generalization Performance of Deep Neural Networks Via The Fisher Information Matrix Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we aim to construct a generalization measure based on the Fisher information matrix of a model, which we show is computationally tractable to compute for large models. |
Chase Goddard ; David Schwab; |
| 132 | Universal Sharpness Dynamics in Neural Network Training: Fixed Point Analysis, Edge of Stability, and Route to Chaos Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We demonstrate that a simple two-layer linear network (uv model) trained on a single training example exhibits all of the essential sharpness phenomenology observed in real-world scenarios. |
Dayal Singh Kalra ; Tianyu He ; Maissam Barkeshli; |
| 133 | Statistical Mechanics of Semantic Compression Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, I map out the phase diagram of this model in an idealized setting in which the elements of a finite but large lexicon all have random embeddings. |
Tankut Can; |
| 134 | Bounds on Learning with Power-law Priors Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We show that any tail broader than Zipfian implies that a learning machine will fail to generalize on unseen data, while a narrower tail limits the number of functions that can be learned. |
Sean Ridout ; Ilya Nemenman ; Ard Louis ; Chris Mingard ; Radosław Grabarczyk ; Kamaludin Dingle ; Guillermo Valle Pérez ; Charles London; |
| 135 | In-depth Analysis of The Learning Process for A Small Artificial Neural Network Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In our study, we investigate the loss landscape and backpropagation dynamics of convergence for the logical exclusive-OR (XOR) gate by means of one of the simplest artificial neural networks composed of sigmoid neurons. |
Xiguang Yang ; Krish Arora ; Michael Bachmann; |
| 136 | Understanding Neural Network Generalizability from The Perspective of Entropy Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In statistical physics, the flatness of a minimum in an energy landscape can be quantified by entropy. Therefore, we calculated the entropy of the loss-function landscape of NNs using Wang-Landau molecular dynamics and explored the potential correlation between such entropy and NNs’ generalizability. |
Entao Yang ; Xiaotian Zhang ; Ge Zhang; |
| 137 | Deep Variational Multivariate Information Bottleneck Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a unifying principle rooted in information theory to rederive, generalize, and design variational methods. |
K. Michael Martini ; Eslam Abdelaleem ; Ilya Nemenman; |
| 138 | Nonlinear Classification of Neural Manifolds with Context Information: Geometrical Properties and Storage Capacity Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A commonly adopted approach to tackle this problem involves the analysis of statistical and geometrical attributes that link neural activity to task implementation in high-dimensional spaces. Here, we explore an analytically-solvable classification model that derives its decision-making rules from a collection of input-dependent "expert" neurons, each associated with distinct contexts through half-space gating mechanisms. |
Francesca Mignacco ; Chi-Ning Chou ; SueYeon Chung; |
| 139 | On Quantum Backpropagation, Information Reuse, and Cheating Measurement Collapse Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We show that achieving backpropagation scaling is impossible without access to multiple copies of a state. With this added ability, we introduce an algorithm with foundations in shadow tomography that matches backpropagation scaling in quantum resources while reducing classical auxiliary computational costs to open problems in shadow tomography. |
Amira Abbas; |
| 140 | Connecting Channel Expressiveness to Gradient Magnitudes and Noise Induced Barren Plateaus Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we propose several measures of expressiveness for quantum channels and study their properties, highlighting how average non-unitary channels differ from average unitary channels. |
Matthew Duschenes ; Diego García-Martín ; Martin Larocca ; Zoe Holmes ; Marco Cerezo; |
| 141 | Generalization Error in Quantum Machine Learning in The Presence of Sampling Noise Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we employ methodologies from statistical mechanics to calculate the learning curve of a generic quantum machine learning system, when the training set contains a large but finite number of samples. |
Fangjun Hu ; Xun Gao ; Hakan Tureci; |
| 142 | Demonstration of A Quantum Machine Learning Algorithm Beyond The Coherence Time Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we introduce a machine learning algorithm, NISQRC, that can be trained to reliably produce inference on a signal of arbitrary length, not limited by the depth of the circuit. |
Hakan Tureci ; Fangjun Hu ; Saeed Khan ; Nicholas Bronn ; Guilhem Ribeill ; Gerasimos Angelatos ; Graham Rowlands; |
| 143 | Reduction of Finite Sampling Noise in Quantum Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we present a new technique to mitigate the finite-sampling noise in QNNs. |
David Kreplin ; Marco Roth; |
| 144 | Full-stack Quantum Machine Learning in High Energy Physics Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: With this talk we discuss the potentialities of Qibo as full-stack environment to test and deploy QML procedures. To do this, we present a series of tests we performed on a superconducting device to improve a gradient descent training on chip with the aim of fitting the proton Parton Distribution Functions (PDFs). |
Matteo Robbiati; |
| 145 | Quantum Inception Score As An Expressivity Measure of The Quantum Generative Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose the quantum inception score, which quantifies the richness of the expressive power of the quantum generative models. |
Akira Sone ; Naoki Yamamoto; |
| 146 | Problem-informed Graphical Quantum Generative Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose a framework for using Markov networks in the construction of quantum circuit Born machines, that outperform previous problem-agnostic models. |
Bence Bakó ; Zsófia Kallus ; Zoltan Zimboras; |
| 147 | Generative Quantum Machine Learning Via Denoising Diffusion Probabilistic Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Inspired by the classical counterpart, we propose the quantum denoising diffusion probabilistic models (QuDDPM) to enable efficiently trainable generative learning of quantum data. |
Bingzhi Zhang ; Peng Xu ; Xiaohui Chen ; Quntao Zhuang; |
| 148 | Reinforcement Learning-Assisted Shot Assignment for Improved Convergence in Variational Quantum Eigensolver Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work introduces reinforcement learning-assisted shot assignment strategies to mitigate measurement errors and improve VQE convergence. |
Linghua Zhu ; Senwei Liang ; Chao Yang ; Xiaosong Li; |
| 149 | Optimizing ZX-Diagrams with Deep Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we bring together ZX-diagrams with reinforcement learning, a machine learning technique designed to discover an optimal sequence of actions in a decision-making problem, and show that our reinforcement learning agent can significantly outperform other optimization techniques like a greedy strategy and simulated annealing. |
Maximilian Nägele ; Florian Marquardt; |
| 150 | Simulating Structural Phase Transitions with Simple Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We employ molecular dynamics simulations to shed light on different structural transitions: between liquid phases and solid crystals, as well as between different crystalline phases. |
Julia Dshemuchadse; |
| 151 | Natural Language Processing for Material Properties Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we introduce a transformer-based neural network model for representing crystalline materials. |
Nhat Huy Tran ; Momei Fang ; Fangze Liu ; Zhantao Chen ; Chunjing Jia; |
| 152 | A Novel Graph Machine Learning Model for Structure-to-Property Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, using degree-based scalers may inadequately represent an atom’s interactive environment, resulting in poor predictions for molecule and crystal structure-based properties. To address this, we propose adaptive-ChemGNN, an MPNN tailored for the atom’s local interactive environment. |
Yong Wei ; Hanning Chen ; Yinning Zhang ; Jing He ; Yuewei Lin; |
| 153 | Thermodynamic Speed Limits As A Design Principle for Dissipative Materials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, I will discuss thermodynamic speed limits on dissipation as a possible design principle that balances the tradeoff between efficiency and speed across length and timescales. |
Jason Green; |
| 154 | Artificial Intelligence Guided Study of Superconductors Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a data-driven framework for accelerating the discovery of novel BCS superconductors. |
Trevor David Rhone ; Dylan Sheils ; Romakanta Bhattarai ; Yoshiharu Krockenberger; |
| 155 | Learning Crystal Structure from Powder X-Ray Diffraction Data Using Invariants Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a framework-independent machine learning (ML) method to determine unit cell parameters and classify Bravais lattices from powder X-Ray diffraction (XRD) data. |
Elyssa Hofgard ; Tess Smidt ; Aria Tehrani; |
| 156 | Mapping The ICSD Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, I will discuss mapping the inorganic materials that have been reported in the ICSD [1]. |
William Ratcliff ; Paul Kienzle ; Karen Cao ; Ichiro Takeuchi; |
| 157 | Structure Complements: A New Materials Taxonomy Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a new paradigm of materials taxonomy, dubbed "structure complements," by generalizing anti-structures (or inverse structures). |
Kyle Miller ; James Rondinelli; |
| 158 | TitleOral: Accelerating High-throughput Screening of High Thermal Conductivity Metal-organic Frameworks with Active Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To achieve this objective, we performed a high-throughput screening using a combination of classical molecular dynamics (MD) simulations with Green-Kubo calculations and surrogate models based on geometric message-passing graph neural networks. |
Hariharan Ramasubramanian ; Meiirbek Islamov ; Alan McGaughey ; Christopher Wilmer; |
| 159 | Data-driven Studies of Magnetic Van Der Waals Heterostructures Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A very large number of candidate materials (~10 7) are considered in the study, which are formed by making chemical substitutions at the atomic sites of MnBi 2Te 4/Bi 2Te 3. |
Romakanta Bhattarai ; Peter Minch ; Trevor David Rhone; |
| 160 | Symmetry-equivariant Neural Networks for Understanding and Designing Physical Systems: Advances, Challenges, and Opportunities Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: ENNs avoid brute-force data augmentation that traditional neural networks require to understand these transformations and are extremely data-efficient, they make more accurate predictions and need less data to do so. In this talk, I will give an overview of recent advances in ENNs and their application to physical systems, describe challenges in training and scaling these methods, and highlight unexplored opportunities in ENN techniques including applying these methods more broadly. |
Tess Smidt; |
| 161 | Stochastic Force Inference Via Density Estimation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose an approach that relies on the probability flow associated with an underlying diffusion process to infer an autonomous, nonlinear force field interpolating between the distributions. |
Victor Chardès ; Suryanarayana Maddu ; Michael Shelley; |
| 162 | Ab Initio Uncertainty Quantification in Scattering Analysis of Microscopy Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce another paradigm that defines a probabilistic generative model from the beginning of data processing and propagates the uncertainty for parameter estimation, termed the ab initio uncertainty quantification (AIUQ). |
Mengyang Gu ; Yue He ; Xubo Liu ; Yimin Luo; |
| 163 | Combining Physics with Multi-fidelity Computation for Improved Bayesian Active Learning Based Exploration Over Lattice Hamiltonian System Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The proposed approach aims to avoid learning unphysical behavior and invariant to low-fidelity approximations and can be universally suitable for rapid multi-fidelity-based exploration over expensive systems. |
Arpan Biswas ; Sai Mani Prudhvi Valleti ; Rama Vasudevan ; Sergei Kalinin ; Maxim Ziatdinov; |
| 164 | Characterizing Inference of Non-reciprocal Connections in The Kinetic Ising Model Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Specifically, we tune the reciprocal coupling strength, non-reciprocal coupling strength, and the temperature of the kinetic Ising model to tune between a quasi-ordered state, disordered state, and the more interesting dynamical swapping state, in which sub-populations magnetize out of phase from each other. |
Peter Fields ; Cheyne Weis ; Stephanie Palmer ; Peter Littlewood; |
| 165 | Data-Enabled Coarse-Graining of Confined Simple Liquids Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While much attention has been focused on homogenous systems, application to confined fluids remains a challenge. To address this, we present a data-driven framework aimed at determining coarse-grained Leonard-Jones (LJ) potential parameters for simple liquids within confined systems. |
Ishan Nadkarni ; Haiyi Wu ; Narayana Aluru; |
| 166 | Self-supervised Deep Learning for Intense Charged Particle Beam Dynamics with Hard Physics Constraints Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The simulation of the dynamics of such beams can be extremely computationally expensive based on O(n^2) individual particle-to-particle interactions, where n=1.25×10^10 for a 2 nC bunch. In this talk we present recent results on developing deep neural network-based self-supervised deep learning for such intense charged particle beam dynamics with guaranteed hard physics constraints. |
Alexander Scheinker ; Reeju Pokharel; |
| 167 | Learning Biophysical Energy Functions from Protein Structure Data with Physically-informed Equivariant Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we show that a rotationally symmetric neural network trained on protein structure data, which has demonstrated the ability to learn an effective biophysical potential from data, can be used to modify input coordinates of a protein structure to reflect new desired outputs. |
Kevin Borisiak ; Armita Nourmohammad ; Michael Pun ; Gian Marco Visani; |
| 168 | Junyu Liu Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Title: A grant unification theory of variational quantum algorithms Abstract: We point out that the so-called quantum neural tangent kernel, the trace of Hessian matrix of the mean-square loss function, plays a significant role in the dynamics of variational quantum circuits in quantum machine learning algorithms. |
Junyu Liu; |
| 169 | Dynamical Phase Transition in Quantum Neural Networks with Large Depth Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we identify a dynamical phase transition in the training dynamics of quantum neural networks with large depth. |
Bingzhi Zhang ; Junyu Liu ; Liang Jiang ; Quntao Zhuang; |
| 170 | Expressive Quantum Circuits Provide Inherent Privacy in Federated Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we introduce federated learning with variational quantum circuit model built using expressive encoding maps coupled with overparameterized ansatze. |
Niraj Kumar ; Jamie Heredge ; Changhao Li ; Shree Hari Sureshbabu ; Shaltiel Eloul ; Marco Pistoia; |
| 171 | Automatic Generation of Quantum Neural Networks with Reinforcement Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we discuss the automatic generation of QNNs with a model-based reinforcement learning approach. |
Frederic Rapp ; Marco Roth; |
| 172 | Approximately Symmetric Neural Quantum States for Quantum Spin Liquids Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, for arbitrary Hamiltonians in a given spin liquid phase, the exact form of the symmetry operators is often not known. In order to exploit these symmetries, we propose an approximately group-invariant neural network as a variational ansatz for the ground state wavefunction. |
Jack Kemp ; Dominik Kufel ; Norman Yao; |
| 173 | Deep Learning Using Quantum Stochastic Switches Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A learning machine, by contrast with a machine learning algorithm, is an analogue physical system that learns. |
Matthew Woolley ; Ethan Sigler ; Gerard Milburn; |
| 174 | Approximate Compilation of Variational Quantum Algorithms Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Nevertheless, current quantum compilers do not effectively leverage the approximate nature of VQA circuits and thus overlook opportunities to optimize executables for quantum computing hardware. In light of this, we present Bifrost, the first quantum compiler that is designed specifically for VQAs and leverages their resilience to deformation via approximate compilation. |
Runzhou Tao ; Yunong Shi ; Sashwat Anagolum ; Ronghui Gu ; Vivek Yanamadula; |
| 175 | On The Use of Physics in Machine Learning for Imaging and Quantifying Complex Processes Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we will discuss more extensively the quantitative properties of dynamic Peace, i.e. when the particle size distribution itself is evolving due to chemical or mechanical interactions. |
George Barbastathis ; Qihang Zhang ; Richard Braatz ; Allan Myerson ; Charles Papageorgiou ; Wenlong Tang ; Yi Wei ; Neda Nazemifard ; Deborah Pereg ; Ajinkya Pandit ; Shashank Muddu ; Sandip Mondal ; Daniel Roxby ; Jongyoon Han; |
| 176 | Energy Frontier Exploration Using Particle Physics and AI Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: I In this talk, I will provide a brief overview of key applications of AI/ML to fundamental physics research at the energy frontier of particle physics and describe several future directions in areas including explainable AI, uncertainty quantification, anomaly detection and real-time AI systems that will significantly enhance the scientific capabilities and opportunities of future experiments. |
Mark Neubauer; |
| 177 | Data-driven Medical Image Formation Without A Priori Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: They can be an important medical resource if we can solve a difficult ill-posed inverse problem. |
Michael Insana ; Will Newman; |
| 178 | The Restricted Boltzmann Machine: from The Statistical Physics of Disordered Systems to A Practical and Interpretative Generative Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk I will present our recent work on the Restricted Boltzmann Machine (RBM). |
Aurélien Decelle ; Beatriz Seoane ; Lorenzo Rosset ; Cyril Furtlehner ; Nicolas Bereux ; Giovanni Catania ; Elisabeth Agoritsas; |
| 179 | Image Reconstruction for A Shift Variant Magnetic Particle Imaging System Using Deep Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: One major challenge with single-sided topology comes from the inhomogeneous magnetic fields used for the encoding gradient and the excitation, which make the system inherently shift variant. |
Christopher McDonough ; Christopher Bastajian ; Alycen Wiacek ; Alexey Tonyushkin; |
| 180 | Machine Learning Approaches to Analyzing Atomic Force Microscopy Images of Cross-Linked Polyethylene Pipes Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We use atomic force microscopy-force spectroscopy (AFM-FS) to measure the morphology and mechanical properties of cross-linked polyethylene (PEX-a) pipe. |
Benjamin Baylis ; Michael Grossutti ; John Dutcher; |
| 181 | Harnessing Automation and Machine Learning in Scanning Probe Microscopy to Accelerate Physics Discovery Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we developed automated experimental approaches in scanning probe microscopy (SPM) and investigated ferroelectric polarization switching in response to varied pulse biases (i.e., bias magnitude and duration). |
Yongtao Liu ; Rama Vasudevan ; Maxim Ziatdinov ; Sergei Kalinin; |
| 182 | XLuminA: An Auto-differentiating Discovery Framework for Super-Resolution Microscopy Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we introduce XLuminA, an original computational framework designed for the discovery of novel optical hardware in super-resolution microscopy. |
Carla Rodríguez ; Sören Arlt ; Leonhard Möckl ; Mario Krenn; |
| 183 | Broading The Partisipation of ImageAI Scientists in Cryo-ET Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To democratize image AI research and invite fresh perspectives, we aim to broaden the community of scientists and engineers focusing on bacterial structure identification. |
Braxton Owens; |
| 184 | Disentangle Structure-Spectrum Relationship with Physics-Informed Generative AI Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we overcome the challenge with a new machine learning framework: Rank-constrained Adversarial Autoencoders. |
Xiaohui Qu ; Zhu Liang ; Matthew Carbone ; Wei Chen ; Fanchen Meng ; Eli Stavitiski ; Deyu Lu ; Mark Hybertsen; |
| 185 | Autonomous Classification of Scanning Tunneling Spectroscopy Via Deep Learning with Variational Autoencoders Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We have demonstrated the autonomous classification of STS of several material systems using deep learning. |
Darian Smalley ; Stephanie Lough ; John Thomas ; Masahiro Ishigami; |
| 186 | AARDVARK: Adaptive Automation and Real-time Data Visualization for ARPES Research Kit Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Typical ARPES experiments begin with a time-intensive procedure to manually search for the most spectroscopically ‘ideal’ region of the sample. Our work creates a modular AI/ML pipeline that autonomously controls the experiment during this initial search. |
Matthew Staab ; Eli Rotenberg ; Inna Vishik; |
| 187 | Supervised Learning Study of Raman Spectroscopy Features Characteristic of MOCVD–grown Transition Metal Dichalcogenides Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Leveraging data from 300 growth trials, we use statistical analysis and supervised learning technologies, including tree–based algorithms, to study the relationships between gas chalcogen precursor MOCVD synthesis parameters of MoS 2 thin films and features within Raman spectra of the resulting samples. |
Andrew Messecar ; Chen Chen ; Isaiah Moses ; Wesley Reinhart ; Joan Redwing ; Steven Durbin ; Robert Makin; |
| 188 | Deep Generative Modeling of Infrared Images Provides Signature of Cracking in Cross-Linked Polyethylene Pipe Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This study shows how representation learning by deep generative modeling can significantly enhance the analysis of high-resolution IR images of complex heterogeneous samples. |
Michael Grossutti ; Benjamin Baylis ; John Dutcher; |
| 189 | Accurate, Uncertainty-aware Classification of Molecular Chemical Motifs from Multi-modal X-ray Absorption Spectroscopy Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we present neural network ensemble classifiers for predicting the presence (or lack thereof) of 41 different chemical motifs on small molecules from simulated C, N and O K-edge X-ray absorption near-edge structure (XANES) spectra. |
Deyu Lu ; Matthew Carbone ; Phillip Maffettone ; Xiaohui Qu ; Shinjae Yoo; |
| 190 | Large-Scale Raman Spectrum Calculations in Graphene Using Deep Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Many ad hoc rules have been developed to analyze the obtained spectrum and give them an underlying physical meaning. We aim to improve our understanding of these spectrum and how they relate to atomic compositions by using deep neural networks based on the Schnet 1 architecture, trained on DFT data, and extending their capacities way beyond a few thousands of atoms, while keeping their near ab initio accuracy. |
Olivier Malenfant-Thuot ; Dounia Shaaban Kabakibo ; Simon Blackburn ; Bruno Rousseau ; Michel Côté; |
| 191 | Autonomous Synthesis of Thin Films with Pulsed Laser Deposition Using in Situ Raman and Reflectance Spectroscopy Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The autonomous workflow presented and the PLD platform we developed is applicable to any material that can be grown by PLD. |
Sumner Harris ; Arpan Biswas ; Seok Joon Yun ; Christopher Rouleau ; Alexander A. Puretzky ; Rama Vasudevan ; David Geohegan ; Kai Xiao; |
| 192 | Vision Transformers for X-Ray Spectroscopy and Fluctuation Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work we present a generative technique using ViT which can instantaneously convert detector images to photon maps in the regime of low-photon count spectroscopy for XPFS, showing this model outperforms all current state of the art (classical and ML) techniques, and can also be fine-tuned during an experiment to adapt to new detector parameters. |
Mark Jimenez; |
| 193 | Practical Hybrid Digital-analog Quantum Learning on Rydberg Atom Arrays Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose hybrid digital-analog learning algorithms on Rydberg atom arrays, combining the potentially practical utility of quantum learning and near-term realizability with the rapidly scaling architectures of neutral atoms. |
Kristina Wolinski ; Milan Kornjaca ; Susanne Yelin ; Jonathan Lu ; Lucy Jiao ; Hong-Ye Hu ; Fangli Liu ; Shengtao Wang; |
| 194 | Quantum-enhanced Machine Learning Using Phosphorus-doped Silicon Quantum Dots Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, I will show how we can leverage atomically precise manufacturing of phosphorus dopants in silicon to realise a quantum system for generating features for use in a random quantum feature algorithm. |
Sam Sutherland ; Casey Myers ; Brandur Thorgrimmson ; Joris Keizer ; Matthew Donnelly ; Yousun Chung ; Samuel Gorman ; Michelle Simmons; |
| 195 | Utilizing The Non-interacting Bionic Particle Sampling to Solve Image Classification Tasks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The presentation discusses the design of the encoder, reservoir, and measurement process. |
Akitada Sakurai ; Aoi Hayashi ; William Munro ; Kae Nemoto; |
| 196 | Quantum-enhanced Physical-layer Data Learning with A Variational Sensor Network Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we develop supervised learning assisted by an entangled sensor network (SLAEN) for nonlinear classification. |
Pengcheng Liao ; Bingzhi Zhang ; Quntao Zhuang; |
| 197 | Quadri-partite Quantum-Assisted VAE As A Calorimeter Surrogate Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Simulating a single LHC event with Geant4 currently devours around 1000 CPU seconds, with calorimeter simulations imposing substantial computational demands [2]. To address this challenge, we propose a Quantum-Assisted deep generative model. |
J. Quetzalcoatl Toledo-Marin ; Hao Jia ; Sebastian Gonzalez ; Sehmimul Hoque ; Abhishek Abhishek ; Tiago Vale ; Soren Andersen ; Geoffrey Fox ; Roger Melko ; Maximilian Swiatlowski ; Wojciech Fedorko; |
| 198 | Quantum Hardware-Enabled Molecular Dynamics Via Transfer Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Transfer learning offers a workaround, where one first trains models on larger, less accurate classical datasets and then refines them on smaller, more accurate quantum datasets. We explore this approach by training machine learning models to predict a molecule’s potential energy based on its geometric structure using Behler-Parrinello neural networks. |
Abid Khan ; Bryan Clark ; Prateek Vaish ; Yaoqi Pang ; Brenda Rubenstein ; Michael Chen ; Norm Tubman; |
| 199 | Machine Learning with Near-Term Quantum Computers Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Recent studies on quantum computing simulators and hardware indicate that parametrized quantum circuits used for learning on classical data can achieve results similar to that of classical machine learning models while using significantly fewer parameters. We will present results from these studies in a variety of application areas ranging from image recognition to modeling financial data on up to 20 qubits. |
Sonika Johri; |
| 200 | Quantum Reservoir Computing with Neutral Atom Arrays Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: While it has been considered a promising application for near-term quantum computers, current quantum machine learning methods require large quantum resources and suffer from gradient vanishing issues. To alleviate this, we propose a general-purpose quantum reservoir computing algorithm for neutral atom quantum simulators that is resource-frugal, noise-resilient, and scalable. |
Milan Kornjaca ; Hong-Ye Hu ; Chen Zhao ; Jonathan Wurtz ; Alexei Bylinskii ; Pedro Lopes ; Xun Gao ; Fangli Liu ; Shengtao Wang; |
| 201 | A Practical Quantum Reservoir Computing Platform for Quantum Data Processing Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a QRC implementation of quantum state tomography, which is performed with near-optimal measurement resources and without the need to calibrate any gate sequences. |
Gerasimos Angelatos ; Guilhem Ribeill ; Supantho Rakshit ; Michael Grace ; Leon Bello ; Hakan Tureci; |
| 202 | Practical and Versatile Reservoir-filter for Optimizing Multi-state Qubit Readout Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We demonstrate a reservoir-computing inspired learning scheme [1] for optimal temporal processing of quantum measurement data dominated by noise of a quantum-mechanical origin, such as quantum jumps or added noise of quantum amplifiers, for classification of an arbitrary number of states. |
Saeed Khan ; Ryan Kaufman ; Michael Hatridge ; Hakan Tureci; |
| 203 | Reservoir Computing with Feedback for Quantum State Identification Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Reservoir computing offers a potential solution by substituting a naturally occurring nonlinear dynamical system for the neural network. |
Daniel Soh ; Peter Ehlers ; Hendra Nurdin; |
| 204 | Hierarchy of The Echo State Property in Quantum Reservoir Computing Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, the conventional definition of ESP does not aptly describe possibly non-stationary systems, where statistical properties evolve. To address this issue, we introduce two new categories of ESP: non-stationary ESP designed for possibly non-stationary systems, and subspace/subset ESP designed for systems whose subsystems possess ESP. |
Shumpei Kobayashi ; Kohei Nakajima ; Quoc Hoan Tran; |
| 205 | Optical Label-free Determination of Mitochondrial Dynamics Using Deep Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we present an optical, label-free, deep learning enabled mitochondria detection technique for live mammalian cells and demonstrate the applicability of the proposed method in characterizing the dynamics of mitochondria in HeLa, Neuroglioblastoma, and CHO cells. |
Neha Goswami ; YoungJae Lee ; Gabriel Popescu ; Mark Anastasio; |
| 206 | Longitudinal Interpretability of Deep-Learning Based Breast Cancer Risk Prediction Model Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Each study included four images (two views per breast). |
Zan Klanecek ; Yao Kuan Wang ; Tobias Wagner ; Lesley Cockmartin ; Nicholas Marshall ; Brayden Schott ; Alison Deatsch ; Andrej Studen ; Miloš Vrhovec ; Hilde Bosmans ; Robert Jeraj; |
| 207 | Assessing The Impact of CNN Architectures for Whole Organ Segmentation on Predictive Models of Organ Toxicity Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, the impact assessment of CNN segmentation model architectures on predictive models’ performance is incipient. Here, we perform such assessment on a 18F-FDG PET histogram metrics-based model for predicting organ inflammation. |
Katja Strasek ; Daniel Huff ; Nežka Hribernik ; Victor Fernandes ; Vincent Ma ; Zan Klanecek ; Andrej Studen ; Katarina Zevnik ; Martina Reberšek ; Robert Jeraj; |
| 208 | Spatially Resolved IR Hyperspectral Imaging for Malignant Cell Detection Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To systematically investigate the IR spectral alterations associated with carcinogenesis and tumor progression, we initiated a research program to spatially resolve chemistry from IR hyperspectral imaging of individual cells. |
Proity Akbar; |
| 209 | Radiomics Assisted Machine Learning Model for Predication of Prostate Specific Antigen Levels Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We proposed a machine learning model to predict prostate specific antigen (PSA) levels for intermediate or high-risk prostate cancer patients undergoing definitive treatment course. |
Saad Bin Saeed Ahmed ; Agha Hammad Khan ; Wazir Muhammad; |
| 210 | Deep Learning for Image Analysis of Breast and Prostate Cancer Cell Cultures Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a machine-learning analysis of phase-contrast microscope images of breast cancer (MDA-MB-231) and prostate cancer (PC3) cell cultures. |
Aliakbar Sepehri ; Ian Bergerson ; Yen Lee Loh ; Lucas Bierscheid ; John Wilkinson; |
| 211 | Structure Prediction of Iron Hydrides Across Pressure Range with Transferable Machine-learned Interatomic Potential Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we demonstrate the efficacy of automated and systematic methods for training and validating transferable ML-IAPs through global optimization techniques. |
Hossein Tahmasbi ; Kushal Ramakrishna ; Mani Lokamani ; Attila Cangi; |
| 212 | Development of A Machine Learning Interatomic Potential for Uranium Nitride Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we have extended previous work by developing an MLIP for uranium mononitride (UN). |
Lorena Alzate-Vargas ; Richard Messerly ; Roxanne Tutchton ; Kashi Subedi ; Michael Cooper ; Tammie Gibson; |
| 213 | Fast Generation of Ab Initio Training Data for Large-Scale Applications of Neural Network Potentials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a method to quickly generate a dataset to train a NNP tailored to perform well on the target system of interest. |
Jaesuk Park ; Feliciano Giustino; |
| 214 | Graph-Transformer Model for Direct Band Structure Prediction from Crystal Structures Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We developed the first end-to-end model that directly predicts band structures from crystal structures. |
Weiyi Gong ; Tao Sun ; Hexin Bai ; Jeng-Yuan Tsai ; Haibin Ling ; Qimin Yan; |
| 215 | Global Structure Optimization and Metastable Structure Enumeration Using Polynomial Machine Learning Potentials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We show a procedure for performing structure enumerations, including global structure optimization, accelerated by the polynomial MLPs. |
Atsuto Seko; |
| 216 | Developing Generalizable Machine Learning Models Using Electronic Structure-based Features Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we explore the construction of a feature space that includes the underlying physics of a system by using information obtained from computationally affordable electronic structure calculations, such as Hartree-Fock. |
Clara Kirkvold ; Jason Goodpaster; |
| 217 | Accurate Prediction of Magnetic Properties of Permanent Magnets Using Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Moreover, the theoretical determination of macroscopic coercive properties is poor, largely due to Brown’s paradox. To address this limitation, we employ DFT by incorporating machine learning (ML) to synthesize experimentally measured magnetic properties and utilize micromagnetic modeling. |
Churna Bhandari ; Gavin Nop ; Durga Paudyal; |
| 218 | Uncertainty Quantification for Deep Learning-based Metastatic Tumor Delineation on 68Ga-DOTATATE PET/CT Images Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we compare DL uncertainty quantification (UQ) methods for metastatic tumor delineation. |
Brayden Schott ; Victor Santoro Fernandes ; Zan Klanecek ; Dmitry Pinchuk ; Robert Jeraj; |