Highlights of Data Science (GDS) Talks @ APS 2023 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-2023 presentations in our digest console, which supports more features.
To search for work presented at APS-2023 on a specific topic, please make use of the search by venue (APS-2023) service. To summarize the latest research published at APS-2023 on a specific topic, you can utilize the review by venue (APS-2023) service. To synthesizes the findings from APS 2023 into comprehensive reports, give a try to APS-2023 Research. If you are interested in browsing presentations by author, we have a comprehensive list of all APS-2023 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 2023 March Meeting
| Paper | Author(s) | |
|---|---|---|
| 1 | System Optimization of Superconducting Qubit Readout for Quantum Error Correction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we discuss optimizing a 49 qubit readout suitable for quantum error correction by performing an offline and model based optimization. |
Andreas Bengtsson; Alexander Opremcak; Mostafa Khezri; Daniel Sank; Paul Klimov; Julian Kelly; Jimmy Chen; |
| 2 | Bridging The Reality Gap in Quantum Devices with Physics-aware Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Disorder induced by the unpredictable distribution of material defects is one of the major contributions to the reality gap. We bridge this gap using physics-aware machine learning, in particular, using an approach combining a physical model, deep learning, Gaussian random field, and Bayesian inference. |
David Craig; Hyungil Moon; Federico Fedele; Dominic Lennon; Barnaby van Straaten; Florian Vigneau; Leon Camenzind; Dominik Zumbuhl; G. Andrew Briggs; Michael Osborne; Dino Sejdinovic; Natalia Ares; |
| 3 | Developing Robust Protocols for Calibration of A 25-qubit Annealing Device Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We will provide details on our calibration routines for bringing online a 25-qubit quantum annealing testbed comprising XX single-qubit controls and YY coupler controls, all of which must be characterized individually and as a crosstalk matrix. |
Bryce Fisher; Steven Disseler; Steven Weber; Robert Rood; Cyrus Hirjibehedin; Mallika Randeria; Vladimir Bolkhovsky; John Cummings; Rabindra Das; David Kim; Jeffrey Knecht; Justin Mallek; Bethany Niedzielski; Ravi Rastogi; Kyle Serniak; Donna-Ruth Yost; Scott Zarr; Mollie Schwartz; Steven Weber; William Oliver; Jonilyn Yoder; |
| 4 | System Optimization of Gate Frequencies for Surface Code Quantum Error Correction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, I will introduce the frequency optimization problem and the Snake optimizer [1, 2] that we developed to solve it for Google’s flagship quantum processors. |
Paul Klimov; |
| 5 | Towards Robust Automation of Quantum Dot Bootstrapping Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We develop an automated routine to bridge the gap between the initial device cool-down and a voltage configuration in which other previously developed automation schemes can take over for a multiple quantum dot device. |
Danielle Middlebrooks; Justyna Zwolak; |
| 6 | Cross-architecture Tuning of Silicon and SiGe-based Quantum Devices Using Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Each device needs to be tuned to operation conditions. We give a key step towards tackling this variability with an algorithm that, without modification, is capable of tuning a 4-gate Si FinFET, a 5-gate GeSi nanowire and a 7-gate Ge/SiGe heterostructure double quantum dot device from scratch. |
Brandon Severin; Dominic Lennon; Leon Camenzind; Florian Vigneau; Federico Fedele; Daniel Jirovec; Andrea Ballabio; Daniel Chrastina; Giovanni Isella; Mathieu de Kruijf; Miguel Carballido; Simon Svab; Andreas Kuhlmann; Floris Braakman; Simon Geyer; Florian Froning; Hyungil Moon; Michael Osborne; Dino Sejdinovic; Georgios Katsaros; Dominik Zumbuhl; G. Andrew Briggs; Natalia Ares; |
| 7 | All RF-based Tuning Algorithm for Quantum Devices Using Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: By exploiting their bandwidth and impedance matching, we demonstrate an algorithm that automatically tunes double quantum dots with only radio-frequency measurements. |
Barnaby van Straaten; Federico Fedele; Florian Vigneau; Joseph Hickie; Andrea Ballabio; Daniel Chrastina; Georgios Katsaros; Daniel Jirovec; Natalia Ares; |
| 8 | Automating Microscopy with Machine Learning: from Object Identification to Hypothesis Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: I will propose solutions such as ensemble learning and iterative training (ELIT), deep kernel learning, and structured Gaussian processes allowing for exploring complex systems and discovering structure-property relationships in an autonomous fashion. |
Maxim Ziatdinov; |
| 9 | Automated and Autonomous Scanning Probe Experiments for Manipulating and Measuring Domain Wall Properties in Ferroelectric Thin Films Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: 2 Here, we introduce a new class of automated experiments which use image-based feedback to find domain wall depinning fields. |
Sai Valleti; Yongtao Liu; Bharat Pant; Shivaranjan Raghuraman; Maxim Ziatdinov; Jan-Chi Yang; Ye Cao; Stephen Jesse; Sergei Kalinin; Rama Vasudevan; |
| 10 | Designing Models for Autonomous Small-Angle Scattering Measurements of Industrial Soft Materials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we will cover our efforts to develop tools that can correctly label (i.e., identify, classify, label, cluster) small-angle scattering data of soft-materials. |
Tyler Martin; Peter Beaucage; |
| 11 | A Bayesian Optimized Spectral Recommender System with Dynamic Human-guided Targets for Physics Discovery Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we have extended the BO application where the user sequentially learns and update the target properties as the optimization progress, and thereby build a BO-based spectral recommendation system (BO-SRS). |
Arpan Biswas; Yongtao Liu; Rama Vasudevan; Maxim Ziatdinov; |
| 12 | Updates to An MeV Ultrafast Electron Diffraction (MUED) System for Data Analysis and Control Using Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: An MeV ultrafast electron diffraction (MUED) instrument system, such as is located at the Accelerator Test Facility (ATF) of Brookhaven National Laboratory, is a structural … |
Trudy Bolin; Salvador Sosa Guitron; Aasma Aaslam; Sandra Biedron; |
| 13 | Scaling Laws in Deep Neural Networks: Insights from Statistical Mechanics and Exactly Solvable Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A full understanding — and in particular, a prescriptive theoretical framework — for what governs this scaling is lacking. Towards this end, I will discuss our work introducing a classification of different regimes of behavior — notions of "resolution-limited" and "variance-limited" regimes — based on the mechanistic origins behind the scaling. |
Yasaman Bahri; |
| 14 | Results from A Mapping Between Reinforcement Learning and Non-Equilibrium Statistical Mechanics Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this setting, we derive results in RL that are analogous to the Gibbs-Bogoliubov’s inequality in equilibrium statistical mechanics. We propose methods to iteratively improve this bound based on results from RL. |
Jacob Adamczyk; Argenis Arriojas Maldonado; Stas Tiomkin; Rahul Kulkarni; |
| 15 | The Onset of Variance-Limited Behavior for Neural Networks at Finite Width and Sample Size Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, at a training set size, the finite-width network generalization begins to worsen compared to the infinite width performance. We empirically study the transition from the infinite width behavior to this variance-limited regime as a function of training set size and network width and network initialization scale. |
Alexander Atanasov; Cengiz Pehlevan; Blake Bordelon; Sabarish Sainathan; |
| 16 | Feature Learning and Overfitting in Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Yet, understanding when and how this feature learning improves performance remains a challenge: for example, for a fixed task such as classifying images, feature learning is beneficial in modern architectures but detrimental in standard fully-connected feed-forward networks. Here we propose an explanation for this puzzle, by showing that feature learning can result in poor generalization performances as it leads to a `sparse’ neural representation, where only a fraction of the connection in the original network are active. |
Francesco Cagnetta; |
| 17 | Flatter, Faster; Scaling Momentum for Optimal Speedup of SGD Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we study implicit bias arising from the interplay between SGD with label noise and momentum in the training of overparametrized neural networks. |
Aditya Cowsik; Tankut Can; Paolo Glorioso; |
| 18 | Statistical Mechanics of Infinitely-Wide Convolutional Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a stylised teacher-student framework where a CNN is trained on the output of another CNN with random weights. |
Alessandro Favero; Francesco Cagnetta; Matthieu Wyart; |
| 19 | Phase Diagram of Training Dynamics in Deep Neural Networks: Effect of Learning Rate, Depth, and Width Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We systematically analyze optimization dynamics in deep feed-forward neural networks (DNNs) trained with stochastic gradient descent (SGD) over long time scales and study carefully the effect of learning rate, depth, and width of the neural network. |
Dayal Singh Kalra; Maissam Barkeshli; |
| 20 | Generative Probabilistic Matrix Model of Data with Different Low-dimensional Latent Structures Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The model’s special cases include hierarchical clusters, sparse mixing, and non-negative mixing. We describe the correlation and eigenvalue distributions of these patterns within the general model and discuss how our model can be used to generate structured training data for supervised learning. |
Philipp Fleig; Ilya Nemenman; |
| 21 | The Evolution of The Fisher Information Matrix During Deep Neural Network Training Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: al. 2021), but further study is required. Here, we study the evolution of the Fisher Information Matrix throughout training in both the early and late phase, and identify a number of dynamical signatures of its behavior. |
Chase Goddard; David Schwab; |
| 22 | When Does Dual Dimensionality Reduction Perform Better Than Single Dimensionality Reduction? Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we use a generative model of multivariate correlated data and linear dimensionality reduction approaches to carefully explore under which conditions DDR methods outperform independent approaches. |
Eslam Abdelaleem; K. Michael Martini; Ahmed Roman; Ilya Nemenman; |
| 23 | Physics-Informed Featurization of Spectral Functions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We investigate two methods for approximating spectral functions via rational approximations, i.e., approximations as a ratio of two polynomials. |
Shubhang Goswami; Kipton Barros; Matthew Carbone; |
| 24 | Efficient Modelling of Ge15Te85 Using Active Learning Methods Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We discuss active learning, compare training methods, and evaluate the ability of trained MLIPs to match experimentally known quantities of Ge 15Te 85. |
Thomas Arbaugh; Francis Starr; |
| 25 | A Simple Model for Grokking Modular Arithmetic Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk I will present a simple neural network that groks a variety of modular arithmetic tasks. |
Andrey Gromov; |
| 26 | Teaching Core-Hole Spectroscopy to A Deep Neural Network Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Deep neural networks (DNNs) – multilayer machine-learning models that are able to extract and learn patterns represented in data without hand-coded heuristics – are transforming what we can do, and the way we do it, across the physical sciences. XANESNET is a DNN for instantaneous simulations of X-ray absorption spectra (XAS); the XANESNET Project is about addressing the challenge of delivering detailed, high- level theoretical simulations that can capture the complex underlying physics of these experiments but that are – at the same time – fast, affordable, and accessible enough to appeal to beamline users. |
Conor Rankine; Thomas Penfold; |
| 27 | AutoML-accelerated EELS/XAS As An Advanced Structure Characterization Tool Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Although there are both experimental and computational methods to determine these nanoscale structures, they both possess limitations which demonstrate the difficulty of nanoscale structural determination, especially for systems with defects. We aim to tackle this problem and conduct structure characterization by combining ab initio simulations, experimental acquisition, and machine learning (ML) techniques. |
Haili Jia; Gihyeok Lee; Yiming Chen; Wanli Yang; Maria Chan; |
| 28 | Featurization Approaches for Machine Learning of X-ray Absorption Spectra Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this presentation, we will benchmark both the reduced dimension features and overcomplete representation to unveil the optimal representation of spectroscopy data. |
Yiming Chen; Maria Chan; Shyue Ping Ong; Chengjun Sun; Steve Heald; chi chen; |
| 29 | Multi-code Benchmark on Ti K-edge X-ray Absorption Spectra of Ti-O Compounds Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we benchmarked Ti K-edge XAS simulations of ten representative Ti-O binary compounds, which we refer to as the Ti-O-10 dataset, using three state-of-the-art codes: XSPECTRA, OCEAN and exciting. |
Fanchen Meng; Benedikt Maurer; Fabian Peschel; Sencer Selcuk; Mark Hybertsen; Xiaohui Qu; Christian Vorwerk; Claudia Draxl; John Vinson; Deyu Lu; |
| 30 | Deep Learning and Infrared Spectroscopy: Representation Learning with A Β-Variational Autoencoder Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This study shows how deep learning architectures like β-VAE can enhance the analysis of spectroscopic data of complex heterogeneous systems. |
Michael Grossutti; John Dutcher; |
| 31 | A Machine Learning Framework for Raman Spectrum Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we apply machine learning methods to obtain Raman spectra from accessible structural and atomic properties. |
Nina Andrejevic; Michael Davis; Mingda Li; Maria Chan; |
| 32 | AI-powered Biotechnology Platform of Single-cell Raman Micro-spectroscopy Enables High-resolution Dynamical Phenotyping Study of Bacterial Growth and Cellular Heterogeneity Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Progresses in single-cell Raman micro-Spectroscopy (SCRS) technologies and automated measurements rapidly yield large spectroscopic datasets that require advanced artificial intelligence (AI)-powered data analytics to discover biological mechanisms in high-resolution and non-invasive manner. We developed this AI-powered SCRS biotechnology platform RamanomeSpec with 4 modules to uncover bacterial phenotypic dynamics, cellular heterogeneity, and identification using machine and deep learning algorithms. |
Zijian Wang; Jenny Kao-Kniffin; Eric Craft; Matthew Reid; Andrea Giometto; Kilian Weinberger; April Gu; |
| 33 | EllipsoNet: Deep-learning-enabled Optical Ellipsometry for Complex Thin Films Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we propose a computational ellipsometry approach based on a conventional tabletop optical microscope and a deep learning model called EllipsoNet. |
Ziyang Wang; |
| 34 | Exploiting Sparsity in Artificial Neural Networks for Spectroscopic Data Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we exploit lottery tickets (i.e., iteratively pruned, sparse networks with the same or slightly better performance than their dense counterparts) for the interpretability of ANNs that were trained for classification and regression on spectroscopic data. |
Jakub Vrabel; Erik Kepes; Pavel Nedelnik; Pavel Porizka; Jozef Kaiser; |
| 35 | Deep Machine Learning The Spectral Function of A Hole in A Quantum Antiferromagnet Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we present a theoretical study of the spectral functions of a mobile hole in the t-t’-t”-J model using a classical machine learning (ML) method, namely K-nearest neighbors (KNN), and a deep ML method, namely fully connected feed-forward neural network (FFNN). |
Weiguo Yin; Jackson Lee; Matthew Carbone; |
| 36 | A Modernized View of Coherence Pathways in Magnetic Resonance Spectroscopy Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In particular, cycling the phase of excitation pulses allows one to isolate signal that arises from particular coherence pathways (i.e. signal that pulses move between particular elements of the density matrix following a particular pattern/pathway), and methods were developed to accumulate the data in a way that isolates the data from a particular pathway while discarding data from undesired pathways. |
John Franck; |
| 37 | Machine Learning for Improvements to Gamma Spectroscopy in Nuclear Fusion Diagnostics Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present the groundwork for a digital Compton suppression algorithm that uses state-of-the-art machine learning techniques to perform Pulse Shape Discrimination. |
Kimberley Lennon; Callum Grove; Joseph Neilson; Chantal Nobs; Lee Packer; Robin Smith; |
| 38 | Variational Onsager Neural Networks (VONNs): A Thermodynamics-Based Variational Learning Strategy for Non-Equilibrium Material Modeling Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a variational learning strategy for the discovery of non-equilibrium equations, through the variational action density from which these equations may be derived. |
Shenglin Huang; Zequn He; Bryan Chem; Celia Reina; |
| 39 | Enhancing Prediction Performance of Reservoir Computing By Multiple Delayed Feedbacks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: As a result of adding delays with small spacing to the Electro-optic oscillator model with filter, a stronger feedback coefficient is needed to destabilize the system’s dynamics. Our study examined the impact of the time delays and the spacing between them on the reservoir computing device’s performance. |
Seyedkamyar Tavakoli; Andre Longtin; |
| 40 | Towards Better Physics Extraction in Images Via Unsupervised Custom Loss Shift- Variational Autoencoders Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we develop a shift invariance variational autoencoder (sh-VAE) with a customized loss function, in an attempt to learn more physically meaningful features. |
Arpan Biswas; Sergei Kalinin; Maxim Ziatdinov; |
| 41 | Dynamical Models from Data, Including Constants of Motion Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The FJet method is introduced for modeling a dynamical system from data; it is based on using machine learning to model the updates of the phase space variables. |
Michael Zimmer; |
| 42 | Machine Learning Inverse Problem Solving for Optical Constants Determination Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we employ machine learning based methods to solve the inverse problem of determining the thickness and optical constants of a material from reflectance and transmittance measurements only. |
Mariana Fazio; Kieran Craig; Marwa Ben Yaala; Bethany McCrindle; Chalisa Gier; Callum Wiseman; Stuart Reid; |
| 43 | Magnetic Iron-cobalt Silicides Discovered Using Machine-learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We employ a machine learning (ML) framework coupled with first principles calculations to discover rare-earth-free magnetic iron-cobalt silicide compounds. |
Timothy Liao; Weiyi Xia; Masahiro Sakurai; Renhai Wang; Chao Zhang; Huaijun Sun; Kai-Ming Ho; Cai-Zhuang Wang; James Chelikowsky; |
| 44 | Development of Ensemble Models for The Growth of Colloidal Spin-on-Glass Materials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Using the sol-gel method to establish versatile functional modifications on various surfaces is furthermore a straight-forward and cost-efficient approach. |
Tim Erdmann; |
| 45 | Exploring Materials Dataspaces By Combining Supervised and Unsupervised Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we discuss a rarely addressed topic – the development of automatic tools to explore the available materials-science data. |
Andreas Leitherer; Angelo Ziletti; Christian Liebscher; Timofey Frolov; Luca Ghiringhelli; |
| 46 | Development of Deep Learning Potentials to Investigate Initial Corrosion Mechanisms Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we develop and assess the applications of Deep Learning Potentials to investigate corrosion mechanisms via Molecular Dynamics (MD) simulations. |
Ridwan Sakidja; Hendra Hermawan; Ayoub Tanji; Peter Liaw; Xuesong Fan; |
| 47 | Machine Learning Potentials for Accelerated Nuclear Fuel Qualification Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To this end, we derive new accurate machine learning (ML) potentials for actinides that provide high-fidelity reproduction of quantum mechanical (QM) forces at the same low cost of classical force fields. |
Richard Messerly; Leidy Lorena Alzate Vargas; Roxanne Tutchton; Michael Cooper; Sergei Tretiak; Tammie Gibson; |
| 48 | Statistical Physics and Geometry of Overparameterization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Modern machine learning often employs overparameterized statistical models with many more parameters than training data points. In this talk, I will review recent work from our group on such models, emphasizing intuitions centered on the bias-variance tradeoff and a new geoemetric picture for overparameterized regression. |
Pankaj Mehta; |
| 49 | Zipf’s Criticality in Learning Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Recently, Zipf’s law has been observed in the distribution of functions which may be produced by a neural network of a given architecture. We show that these results hold true for many learning machines (not necessarily deep networks) in regimes where learning is possible. |
Sean Ridout; Ilya Nemenman; |
| 50 | How SGD Noise Affects Performance in Distinct Regimes of Deep Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Understanding when the noise in stochastic gradient descent (SGD) improves generalization of neural networks remains a challenge, complicated by the fact that nets can operate in distinct training regimes. Here we study how the magnitude of this noise or `temperature’ T affects performance as the scale of initialization α is varied. |
Antonio Sclocchi; Mario Geiger; Matthieu Wyart; |
| 51 | Stochastic Gradient Descent Introduces An Effective Landscape-dependent Regularization Favoring Flat Solutions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The key question is which solution is more generalizable. Empirical studies showed a strong correlation between flatness of the loss landscape at a solution and its generalizability, and stochastic gradient descent (SGD) is crucial in finding the flat solutions. |
Ning Yang; Yuhai Tu; Chao Tang; |
| 52 | Contrastive Learning Through Non-equilibrium Memory Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we show how the simplest form of non-equilibrium memory in each `synapse’ of a network allows for contrastive rules such as equilibrium propagation. |
Arvind Murugan; Adam Strupp; Benjamin Scellier; Martin Falk; |
| 53 | Data-driven Irreversibility Measurement for Biological Patterns Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we use deep learning to reveal tractable, low-dimensional representations of patterns in a canonical protein signaling process, Rho-GTPase system as well as complex Ginzburg-Landau dynamics. |
Junang Li; Chih-Wei Joshua Liu; Michal Szurek; Nikta Fakhri; |
| 54 | Training Elastic Neural Networks with The Hamiltonian Monte Carlo Sampling Algorithm Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we train resource-constrained elastic ANNs by applying the Hamiltonian Monte Carlo method, a variant of the Metropolis-Hastings algorithm used in statistical physics to sample probability distributions presenting a large number of local minima. |
Théophile Louvet; Vincent Maillou; Finn Bohte; Lars Gebraad; Marc Serra-Garcia; |
| 55 | Scalable and Interpretable Machine Learning for Inference in Stochastic Transcriptional Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We use physics-informed machine learning to develop a scalable and general approach for high-throughput inference of transcriptional system kinetics. |
Maria Carilli; |
| 56 | Finding The Function-Determining Subset of Amino Acids in Protein Sequence Data Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Specifically, we consider EBMs’ ability to capture protein sectors, roughly 10 to 20 percent of total sequence positions that correlate strongly with biological functions. |
Peter Fields; Vudtiwat Ngampruetikorn; Rama Ranganathan; David Schwab; Stephanie Palmer; |
| 57 | Machine Learning Driven Automated Scanning Probe Microscopy for Material Discovery: Applications in Ferroelectric and Optoelectronic Materials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, I will discuss our development of ML-driven SPMs for learning the functionality and mechanism of ferroelectric materials and optoelectronic materials in an automated manner. |
Yongtao Liu; Kyle Kelley; Rama Vasudevan; Maxim Ziatdinov; Sergei Kalinin; |
| 58 | Accelerating The Search for High-Performance, Novel Materials with Active Learning – An Example: Thermal Insulators Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we present an active learning framework, that uses an ensemble of expressions found by the sure-independence screening and sparsifying operator (SISSO) approach [2,3], and we domnstrate it for the example of discovering new thermal insulators. |
Thomas Purcell; Matthias Scheffler; Christian Carbogno; Luca Ghiringhelli; |
| 59 | In-silico Discovery of HER/OER Multi-metallic Alloy Electrocatalysts Through Density Functional Theory Calculations and Active Learning and Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Herein, we propose different machine learning frameworks for the efficient search of promising multi-metallic alloys in hydrogen evolution reaction (HER) and oxygen evolution reactions (OER), the two reactions needed to produce green hydrogen. |
Kwak Seung Jae; Minhee Park; Won Bo Lee; YongJoo Kim; |
| 60 | Efficient Discovery of Air Separation Adsorbents Via Multi-Fidelity Bayesian Optimization Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Through this work, we present candidate materials that can selectively separate O2 from N2 at ambient conditions with dramatically decreased energy cost relative to current adsorbents. |
Eric Taw; Yuto Yabuuchi; Kurtis Carsch; Rachel Rohde; Jeffrey Long; Jeffrey Neaton; |
| 61 | Unveil The Unseen: Exploit Information Hidden in Noise Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Noise and uncertainty are usually the enemy of machine learning, noise in the training data leads to uncertainty and inaccuracy in the predictions. However, Wilson’s … |
Bahdan Zviazhynski; Jessica Forsdyke; Janet Lees; Gareth Conduit; |
| 62 | Prediction of Crystal Symmetry Groups for Binary and Ternary Materials from Chemical Compositions Using Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, starting only from the chemical formula, the elemental properties are utilized to develop an accurate predictive ML model for the crystallographic symmetry groups classification, including crystal systems, point groups, Bravais lattices and space groups [1,2]. |
Mohammed Alghadeer; Abdulmohsen Alsaui; Yousef Alghofaili; Fahhad Alharbi; |
| 63 | Statistical Modeling of Frictional Properties: A Machine Learning Approach Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Different regression models have been developed using the selected descriptors, and their accuracies are compared to find the best-optimized model for predicting the frictional energies of bilayers. |
Ranjan Barik; Lilia Woods; |
| 64 | Machine Learning-Based Microstructure Prediction for Laser-Sintered Alumina Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we demonstrate a machine learning-based microstructure prediction that not only predicts the microstructure for unknown conditions but also predicts all features of microstructure (e.g., grain size, grain shape, porosity, etc.). |
Xiao Geng; jianan tang; Jianhua Tong; Dongsheng Li; Hai Xiao; Fei Peng; |
| 65 | Causal Relations in Determining Functionalities in Perovskite Oxides Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A discussion on polarization switching mechanism as understood from a combination of first-principles study and causal relations will be included in the presentation. |
Ayana Ghosh; Saurabh Ghosh; |
| 66 | Machine Learning Prediction of Perovskite Solar Cell Properties Under High Pressure Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we investigate the leading structural features that determine the material properties of the perovskites upon compression. |
Minkyung Han; Chunjing Jia; Yu Lin; Cheng Peng; Feng Ke; Youssef Nashed; |
| 67 | Double Descent, Linear Regression, and Fundamental Questions in Materials Model Building Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: How completely must we span configuration space with our expansions? We address these questions from the perspective of both mathematics and physics and discuss the implications for practical alloy models. |
Gus Hart; |
| 68 | Curie Temperature Prediction Models of Magnetic Heusler Alloys Using Machine Learning Methods Based on First-principles Data from Ab-initio KKR-GF Calculations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We studied multiple descriptor selection methods to determine the most meaningful physical quantities in the given phase space. |
Robin Hilgers; Roman Kovacik; Daniel Wortmann; Stefan Blügel; |
| 69 | Physics Interpretable Ensemble Learning for Materials Property Prediction: Carbon As An Example Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we propose an ensemble learning model consisting of regression trees to predict materials properties, using the formation energy and elastic constants of carbon allotropes as examples. |
Xinyu Jiang; |
| 70 | Unified Graph Neural Network Force-field for The Periodic Table Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Furthermore, many material properties are known to be sensitive to slight changes in bond angles. We present an Atomistic Line Graph Neural Network (ALIGNN), a GNN architecture that performs message passing on both the interatomic bond graph and its line graph corresponding to bond angles. |
Kamal Choudhary; |
| 71 | Structure-motif-based Material Network for Functional Material Discovery Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we will discuss the construction of a material network using a structure-motif-based connection measure algorithm, to identify and categorize materials sharing common properties. |
Anoj Aryal; Huta Banjade; Qimin Yan; |
| 72 | Physically Informed Graph Neural Networks for Prediction of Optical Properties of Solid Materials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We here develop a physically informed graph neural network (GNN) to predict the frequency-dependent dielectric function of solid crystals, from which we can calculate all optical properties. |
Can Ataca; Akram Ibrahim; |
| 73 | Understanding Self-Assembly Behavior with Self-Supervised Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we show several permutation- and rotation-equivariant neural network architectures using attention mechanisms to solve self-supervised tasks on point clouds. |
Matthew Spellings; Maya Martirossyan; Julia Dshemuchadse; |
| 74 | Metric Geometry Tools for Automatic Structure Phase Map Generation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we describe a statistical tool to efficiently obtain a phase map from high-throughput measurements. |
Kiran Vaddi; Karen Li; Lilo Pozzo; |
| 75 | Graph Neural Network Accelerated Generalizable Stress Field Prediction for Mesh-based Finite Element Simulations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In our study, we develop GNN models to predict stress and strain distributions in a body subject to external loads. |
Bowen Zheng; Zeqing Jin; Changgon Kim; Grace Gu; |
| 76 | Modeling The Band Structure of Periodic Crystals with Physics-Informed Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a neural network architecture to model the wavefunction and band structure of a periodic crystal. |
Circe Hsu; Daniel Larson; Gabriel Schleder; Marios Mattheakis; Efthimios Kaxiras; |
| 77 | Using CycleGANs to Construct Training Data for Other Machine Learning Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present an approach to generating "experimental"-like data by employing a cycleGAN to automatically add realistic features and noise profiles to simulated data. |
Abid Khan; Chia-Hao Lee; Pinshane Huang; Bryan Clark; |
| 78 | Contrastive Learning Reveals The Trajectory of Protein Structure Evolution Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The molecular structure of a protein in three-dimensional space can be represented by the spatial distances of all possible amino acid residue pairs, formulating a symmetric … |
Yong Wei; Baofu Qiao; Tao Wei; Hanning Chen; |
| 79 | Geometric Dynamic Variational Autoencoders for Learning Nonlinear Dynamics Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We develop data-driven methods incorporating geometric and topological information to learn parsimonious representations of nonlinear dynamics from observations. |
Ryan Lopez; Paul Atzberger; |
| 80 | Screening The Unexplored Crystal Prototype Space and Inverting XRD Patterns with The WREN Machine-learning Model Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This talk presents the WREN model and demonstrates our recent progress in using it to invert XRD patterns. |
Rickard Armiento; Abhijith Parackal; Rhys Goodall; Felix Faber; Alpha Lee; |
| 81 | Semi and Self Supervised Approaches to Space Group and Bravais Lattice Determination Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: During this talk, I will discuss our work [1] to use neural networks to automatically classifiy Bravais lattices and space-groups from neutron powder diffraction data. |
William Ratcliff; Satvik Lolla; Ichiro Takeuchi; Aaron Kusne; Haotong Liang; |
| 82 | Machine Learning The Electronic Structure of Phase Change Materials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we use machine learning to parameterize a tight-binding ansatz for the electronic structure of complex phase change materials. |
Qunfei Zhou; Suvo Banik; Srilok Srinivasan; Subramanian Sankaranarayanan; Pierre Darancet; |
| 83 | Data-driven Studies of Topological Magnetic VdW Materials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we consider a very large number of candidate materials (~10 4) formed by tuning the chemical composition of AB 2X 4. |
Romakanta Bhattarai; Peter Minch; Trevor David Rhone; |
| 84 | Data-driven Study of Magnetic Anisotropy in Transition Metal Dichalcogenide Monolayers Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We investigate the magnetic and thermodynamic properties of transition metal dichalcogenides of the form AX 2, based on monolayer MnSe 2 using data analytics. |
Peter Minch; Romakanta Bhattarai; Trevor David Rhone; |
| 85 | Using Chemical-formula-based Generalizable Models to Expand The Search Space for Viable Interconnect Materials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: For our stability metrics, we use the energy with respect to the convex hull, and 0K thermodynamic reaction energies with air, water and SiO2. |
Akash Ramdas; Evan Reed; Felipe da Jornada; |
| 86 | How to Search for Stable Inorganic Compounds More Efficiently Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To guide the search towards the most likely stable compounds, several recommendation engines have been developed, varying in their strategy from data mining to machine learning. We conduct a systematic comparison of the performance of previously developed recommendation engines in recovering stable hypothetical compounds in the Open Quantum Materials Database (OQMD), and develop workflows to execute these methods in a highly efficient manner. |
Sean Griesemer; Ruijie Zhu; Koushik Pal; Cheol Park; Logan Ward; Christopher Wolverton; |
| 87 | Integrating Machine Learning with Mechanistic Models for Predicting The Yield Strength of High Entropy Alloys Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we demonstrate a computational approach that integrates mechanistic models with phenomenological and ML models to rapidly predict the temperature-dependent yield strength of high entropy alloys (HEAs) that form in the single-phase face-centered cubic (FCC) structure. |
Shunshun Liu; Kyungtae Lee; Prasanna Balachandran; |
| 88 | Statistics on The Magnetism of Cobalt Compounds: A Database Approach to Discovering New Co-based Ferromagnets Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We propose a method to facilitate the search for novel ferromagnets by creating a database of cobalt-based compounds. |
Journey Byland; Yunshu Shi; David Parker; Jingtai Zhao; Shaoqing Ding; Rogelio Mata; Haley Magliari; Andriy Palasyuk; Sergey Bud’ko; Paul Canfield; Peter Klavins; Valentin Taufour; |
| 89 | Navigating Materials Design Space with Variational Autoencoders to Learn Materials Thermodynamics Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We introduce a definition of materials similarity in (property-ordered) low-dimensional latent spaces, compare it to the materials similarity in the input materials fingerprint space, and demonstrate transferable models of thermodynamic properties. |
Vahe Gharakhanyan; Dallas Trinkle; Snigdhansu Chatterjee; Alexander Urban; |
| 90 | Automatic, Physical Data Extraction from Scientific Publications for Application to Generative Molecular Design in Computational Materials Discovery Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this contribution, we will present a method and research tool that allows the annotation and automatic extraction of physical and chemical data tables from document files. |
Ronaldo Giro; Mohab Elkaref; Hsianghan Hsu; Nathan Herr; Geeth de Mel; Mathias Steiner; |
| 91 | Machine Learned Synthesizability Predictions Aided By Density Functional Theory Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we demonstrate that stability calculated from DFT plays a crucial role in enabling a machine learning model to accurately predict half-Heusler synthesizability. |
Andrew Lee; Suchismita Sarker; James Saal; Logan Ward; Christopher Borg; Apurva Mehta; Christopher Wolverton; |
| 92 | Hypothesis-driven Active Learning Over The Chemical Space Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we introduce a novel approach for active learning of a wide chemical space based on hypothesis learning. |
Ayana Ghosh; Sergei Kalinin; Maxim Ziatdinov; |
| 93 | Artificial Intelligence Guided Materials Discovery of Van Der Waals Magnets Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we will harness AI to efficiently explore the large chemical space of vdW transition metal halides and to guide the discovery of magnetic vdW materials with desirable spin properties. |
Trevor David Rhone; Bethany Lusch; Misha Salim; Haralambos Gavras; Vaishnavi Neema; Daniel Larson; Efthimios Kaxiras; |
| 94 | Design of Β-sheet Forming Antimicrobial Peptides Using Deep Learning and Molecular Dynamics Simulations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, I will discuss our efforts to instantiate a computational workflow for active learning design of AMPs through search space design and molecular dynamics assessment of points in the search space. |
Rachael Mansbach; Samuel Renaud; Lindsay Wright; Mohammadreza Niknam Hamidabad; Natalya Watson; |
| 95 | Improved Knowledge Representation Enables AI-Guided Polymer Design and Experimental Validation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Within the context of polymer chemistry—where experimentalists must navigate a highly complex design space—effective knowledge representation of experimental becomes critical to create useful models with actionable predictions. Here, we detail our efforts on the development of new, extensible open-source tools to enable experimentalists to accurately represent experimental data and facilitate its consumption in AI/ML or informatics pipelines. |
Nathan Park; |
| 96 | The Aerodynamic Characteristics Are Modeled Based on Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This paper analyzes and applies the machine learning methods of "black box" modeling – Classification and regression tree method and shallow learning method. |
Xing Zhao; |
| 97 | Flagging of Unacceptable Segmentations: Monte Carlo Dropout Vs. Deep-Ensembles Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we leveraged the quantification of predictive uncertainty (PU) to flag unacceptable pectoral muscle segmentations in mammograms. |
Zan Klanecek; Tobias Wagner; Yao Wang; Lesley Cockmartin; Nicholas Marshall; Brayden Schott; Ali Deatsch; Miloš Vrhovec; Andrej Studen; Hilde Bosmans; Robert Jeraj; |
| 98 | Numerical Generation and Coating of Single Soot Nanoparticles: Implications for Atmospheric Aging Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work proposes a standalone model that generates bare and coated aggregates, and measures their morphological and transport-derived properties, as well as providing an interface for optical modeling. |
Cyprien Jourdain; Adam Boies; Jonathan Symonds; |
| 99 | Structural Investigation of Small Molecule Selectivity for Cardiolipin Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: An automated approach for identifying the chemical interactions crucial for binding selectivity of a drug-like compound to a biomolecular target was recently demonstrated [1]. But the mere presence of these interactions is only part of the picture, in this work we investigate the structure-property relationship of a small molecule candidate with respect to target selectivity. |
Bernadette Mohr; Tristan Bereau; Diego van der Mast; |
| 100 | Machine Learning Application for Astrophysics: A Case Study for Black Hole Images and Strong Gravitational Lensing Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, I will cover some of the recent development of deep learning on several astrophysics projects including supermassive black holes (SMBH), and strong gravitational lensing. |
Joshua Yao-Yu Lin; |
| 101 | Fusion for Reducing Domain Specificity in Computer Vision Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: More recently, synthetic datasets like FlyingThings3D, which contains random everyday objects from many domains flying along random trajectories through space, have attempted to reduce domain specificity by doing away entirely with scene structure. In this work we propose that the answer to the challenge of creating general perception systems is to recognise that different models will have different domains in which they perform well, and to fuse the estimates produced by separate perception models that are each "experts" in their own domains. |
Laura Brandt; Nicholas Roy; |
| 102 | Physics-constrained 3D Convolutional Neural Networks for Relativistic Electrodynamics Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a physics-constrained neural network (PCNN) approach to calculating the electromagnetic fields of intense relativistic charged particle beams via 3D convolutional neural networks. |
Alexander Scheinker; Reeju Pokharel; |
| 103 | Image Classification Via Reversible Analog Superconducting Dynamics Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This talk discusses the reversible limit of analog computing, presenting simulations of image classification using a network of superconducting-based analog flux parametrons (AFP 2). |
Ian Christie; |
| 104 | Machine Learning-Based Classification of Irregular Shape Defects in Metal Additive Manufacturing Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We are developing algorithms for recognition of internal material defects in metal additive manufacturing from images obtained with pulsed thermal tomography (PTT). |
Elaine Jutamulia; Victoria Ankel; Wei-Ying Chen; Alexander Heifetz; |
| 105 | Deep Learning Based Super-resolution Models for Accelerating Multiphysics Simulations of Laser Powder Bed Fusion Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Multiphysics simulation methods can describe the three-dimensional dynamics of the melt pool, but are computationally expensive at the resolutions required for accurate predictions. Therefore, in this work, we develop deep learning based super-resolution models to map low-resolution simulations of the melt pool temperature field to high-resolution simulations of the temperature field, avoiding the computational expense of performing multiple high-resolution simulations for analysis. |
Francis Ogoke; Quanliang Liu; Olabode Ajenifujah; Amir Barati Farimani; |
| 106 | Jacobians in Deep Neural Networks : Criticality and Beyond Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: I will begin my talk by formulating criticality in terms of Jacobians-norm. Using this formulation, I will show that it is possible to design networks that are “everywhere-critical”, i.e. critical irrespective of the choice of initialization; by incorporating LayerNorm/BatchNorm and residual connections. |
Darshil Doshi; Tianyu He; Andrey Gromov; |
| 107 | AutoInit: Automatic Initialization Via Jacobian Tuning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We will introduce a new and cheap algorithm, that allows one to find a good initialization automatically for general architectures. |
Tianyu He; Darshil Doshi; Andrey Gromov; |
| 108 | A Machine Learning Framework to Analyze and Optimize The Print Parameters of Direct Ink Writing (DIW) Systems Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we present a data-driven machine learning (ML) framework for rapidly analyzing and optimizing the print parameters to meet a designer’s desired printability metrics. |
Aldair Gongora; Deirdre Newton; Timothy Yee; Zachary Doorenbos; Brian Giera; Thomas Yong-Jin Han; Kyle Sullivan; Jennifer Rodriguez; |
| 109 | Odor Discrimination and Identification By Graphene-based Electronic Nose System Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we will present the odor discrimination and identification performance of graphene nanosensor-based electronic olfaction system. |
Gianaurelio Cuniberti; Shirong Huang; Alexander Croy; Bergoi Ibarlucea; |
| 110 | Combining Generative Modeling and Genetic Algorithm for Atomistic Structure Search Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We developed a multi-objective genetic algorithm, FANTASTX (Fully Automated Nanoscale to Atomistic Structures from Theory and eXperiment) software, where we combined the theoretical tools with experimental data to determine the atomistic structure of experimentally observed materials. |
Venkata Surya Chaitanya Kolluru; Davis Unruh; Joshua Paul; Maria Chan; |
| 111 | Using Density Functional Theory and Machine Learning to Predict The Binding Energies of Metal-organics to Organic Functional Groups for Hybrid Material Creation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: VPI has applicability in a number of industrially relevant fields including the creation of novel organic-inorganic hybrid membranes which have shown enhanced stability in organic solvents, while retaining high permeance and selectivity. Motivated by this application, this work uses density functional theory (DFT) to explore chemical interactions occurring during the VPI of polymer of intrinsic microporosity (PIM-1, a polymeric membrane material)with trimethylaluminum(TMA) and its co-reaction with water. |
Yifan Liu; |
| 112 | Self-Supervised Learning for Material Property Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Drawing inspiration from the developments in SSL, we introduce a new framework Crystal Twins. |
Rishikesh Magar; Amir Barati Farimani; |
| 113 | Development Strategies and Hyperparameter Optimization of Deep Learning Potentials for Multi-component and Multi-phase Nickel-based Superalloys Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we developed Deep Learning interatomic potentials to model a multi-phase and multi-components system of Ni-based Superalloys. |
Marium Mostafiz Mou; Matthew J. Kindhart; Jared Shortt; Ridwan Sakidja; |
| 114 | Accelerated Designing of Superhard B-C-O Compounds Using Machine Learning and DFT Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Herein, we attempt to accelerate the search for superhard B-C-O compounds by developing machine learning (ML) models for rapid prediction of elastic moduli as proxy properties, followed by subsequent estimation of hardness using Tian’s empirical formula [1]. |
Madhubanti Mukherjee; |
| 115 | Comparing Structural Representations of Grain Boundaries Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We predict grain boundary energy with each representation in a machine-learned model. |
Braxton Owens; |
| 116 | Benchmarking and Optimization of UF3 Machine Learning Potential on Solids Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Ab initio calculations offer a promising theory-guided approach to materials discovery and design. |
Pawan Prakash; Stephen Xie; Hendrik Krass; Ajinkya Hire; Peter Hirschfeld; Matthias Rupp; Richard Hennig; |
| 117 | Evaluation of Thermal Properties of Extended 2D Materials Using Gaussian Approximation Potentials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In recent years, atomically thin two-dimensional materials (2DM) have gained attention due to their flexibility and extraordinary thermal and electronic properties for technological applications. By combining density functional theory (DFT) with Boltzmann transport equation (BTE) it is possible to predict thermal transport properties accurately of these materials; however, the computational cost could be prohibitive for high-throughput calculations or for more realistic simulations with larger super-cell sizes. |
Alvaro Vazquez-Mayagoitia; Tugbey Kocabas; Cem Sevik; Murat Keceli; |
| 118 | Proton Dynamics Simulations of Solid-acid Electrolytes Using Active Learning and Equivariant Neural Network Force Fields Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we develop machine learning interatomic force fields for CsH2PO4 and CsHSO4 superprotonic conductors combining ab-initio accuracy with scalability to large system sizes and nanosecond time scale. |
Menghang (David) Wang; Cameron Owen; Yu Xie; Simon Batzner; Albert Musaelian; Anders Johansson; Boris Kozinsky; |
| 119 | Polymer Property Prediction Via Pre-trained Large Language Model Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we present TransPolymer, a Transformer-based language model built on self-attention for polymer property prediction. |
Yuyang Wang; Changwen Xu; Amir Barati Farimani; |
| 120 | Performance Boosting Portable Acceleration of SISSO++ for Symbolic Descriptor Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we present an updated algorithm that uses the Kokkos performance-portable programming model to offload the performance-critical region of our algorithm to accelerators, such as Nvidia or AMD GPUs [4]. |
Yi Yao; Matthias Scheffler; Christian Carbogno; Luca Ghiringhelli; Thomas Purcell; |
| 121 | First-Principles-Informed Machine Learning Study of Defects on The Lithium Metal Surface Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: These interfaces are disordered on the order of microns and so it is critical to understand the relationship between the microscale energetics and mesoscale. Here, we introduce machine learning (ML) as a way to connect these two scales. |
Hao Yu; Madison Morey; Tianlun Huang; Kubra Cilingr; Ziqing Zhao; Emily Ryan; Brian Kulis; Sahar Sharifzadeh; |
| 122 | Flat Bands in Full-Heusler Crystals – Statistical Analysis with Periodic Table Deep Learning Model Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we propose a convolutional neural network classification model, which only has the periodic table as the input and thus is called periodic table representation (PTR) classifier, to explore flat bands along the high-symmetry paths around the Fermi level and search for the physics behind it. |
xiuying zhang; |
| 123 | Refinement of Training Schemes for Machine-Learning Interatomic Potentials and Its Applications Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: It plays a role in suppressing the extra heat flux generated by the arbitrariness. In the talk, I will discuss the recent progress in the development of MLIP training scheme and its applications. |
Kohei Shimamura; |
| 124 | Benchmarking Machine-learned Interatomic Potential Methods for Reactive Molecular Dynamics at Metal Surfaces Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we compare different families of MLIPs, from atomic cluster expansion (ACE), invariant DNN-based SchNet to novel equivariant neural networks such as PaiNN and MACE on the example of reactive molecular hydrogen scattering on copper. |
Wojciech Stark; Julia Westermayr; Cas van der Oord; Gabor Csanyi; Reinhard Maurer; |
| 125 | Fast and Scalable Uncertainty Estimates in Deep Learning Interatomic Potentials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this project, we propose a method to estimate predictive uncertainty using only a single neural network along with a computationally-inexpensive Gaussian Mixture Model, eliminating the need for an ensemble. |
Albert Zhu; Simon Batzner; Albert Musaelian; Boris Kozinsky; |
| 126 | Predicting Vapor-Liquid Equilibria and Phase Transitions with Machine-Learned Interatomic Potentials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The present work has trained state-of-the-art ML-IAPs (SNAP, POD, Allegro) for Al over a wide range of phase regimes (0.2-3.0 and 933-10,000 ) that are challenging to model with any other simulation method. We demonstrate the efficiency of these atomic representations by reaching quantum-mechanical accuracy in small dataset and then perform large-scale molecular dynamics simulations to predict the vapor-liquid phase equilibrium and the critical point. |
Mitchell Wood; Normand Modine; Dionysios Sema; Ember Sikorski; Stan Moore; Nicolas Hadjiconstantinou; |
| 127 | Numerical Modeling of Hydrogen Absorption in Metal Hydrides Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We will present preliminary results to evaluate the accuracy and speedup enabled by this approach. |
Olivier Nadeau; Gabriel Antonius; |
| 128 | Deep Learning Image Formation in Medical Imaging Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This presentation will cover emerging Deep Imaging approaches, with emphasis on application to volumetric x-ray imaging for point-of-care imaging and interventional radiology applications. |
Alejandro Sisniega; |
| 129 | A Phantom Study of X-ray Fluorescence Measurements of Iron and Zinc Concentrations in Superficial Cutaneous Blood Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Future work will assess radiation dose and the effects of varying skin x-ray attenuation on detection and concentration measurement. |
Mihai Gherase; Vega Mahajan; |
| 130 | Electrical Impedance Tomography (EIT) in 3D: Introducing The Sensitivity Method for Biomedical Imaging Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Electrical impedance tomography (EIT) is a noninvasive imaging method whereby electrical measurements on the periphery of a conductor are inverted to map its internal … |
Matthew Grayson; Claire Onsager; Chulin Wang; Charles Costakis; Can Aygen; Lauren Lang; Suzan van der Lee; |
| 131 | Model-based Approaches for Quantitative Dual-energy Cone-beam CT Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present the current efforts in enabling BMD and BME quantification on a dedicated, point-of-care extremity cone-beam CT (CBCT). |
Stephen Liu; Joseph Stayman; Wojciech Zbijewski; |
| 132 | Using Natural Language Processing to Extract Features from Clinical Notes for Medical Physics Quality Assurance Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The restored database, with substantial data filled in by the NLP methods described, will be used to train and deploy an anomaly detection algorithm [1] that detects potentially erroneous radiotherapy prescriptions and assists with medical physics quality assurance. |
Connor Thropp; Laura Buchanan; Timothy Leech; Qiongge Li; Eric Klein; |
| 133 | Machine Learning Enabled Potential Approach for Cardiovascular Risks Prediction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We have introduced a highly sensitive flexible piezoelectric sensor fabricated from a simple solution processable technique. |
Anand Babu; Dipankar Mandal; |
| 134 | NMR Spectroscopic Investigation of The Effect of LDH Inhibitor Sodium Oxamate on Glucose Metabolism in Cancer Cell Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we have investigated via carbon-13 nuclear magnetic resonance the concentration dependence of sodium oxamate and the role of glutamine on [1-13C] glucose metabolism in a variety of cultured cancers cell including renal cell carcinoma (786-O), hepatocellular carcinoma (HepG-2), and glioblastoma (SfXL cells). |
Asiye Asaadzade; Lloyd Lumata; |
| 135 | The Metabolism of Galactose in Hypoxic Cancer Cells Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In preliminary trials, we examined the metabolism of galactose in Colo-205 and LoVo colorectal cancer cells, SFXL and U87 Glioblastoma cells, Miapaca2 pancreatic cancer cells, and HUH-7 liver cancer cells. |
Daniel Anable; Lloyd Lumata; |
| 136 | Sensitivity of QA Testing to Beam Drifts in LINACs: A MC Study Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We started by validating a Monte Carlo model of the Elekta Agility radiation therapy treatment head at three photon treatment energies, 6MV, 10MV and 18MV using GATE/Geant4. |
Alicia Martin; Thad Harroun; Josef Dubicki; |
| 137 | Monte Carlo Simulations of The Effect of Magnetic Field on Deposited Dose in Proton Therapy Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work focusses on the change in deposited dose with field strength applied either along the beam direction or perpendicular to it. |
Mike Sumption; Abdelhai Benali; Lanchun Lu; Nilendu Gupta; E.W. Collings; |
| 138 | Exploring Heavy-Ion Fusion As A Pathway for Production of Indium-111 Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The aims of the study are to suggest new reaction combinations for the production of 111In radionuclide, compare different models, and explore the impact of deformation parameters on the heavy-ion fusion cross-sections and barrier distribution. |
Pete Miller; |
| 139 | Self-assembly of Electronic Materials and The Power of Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This talk will discuss the most mature test case in which we looked at “solvent engineering” to optimize the process by which some novel solar cells are fabricated. |
Paulette Clancy; |
| 140 | How Deep Neural Networks Learn Thermal Phase Transitions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We derive analytical expressions for the optimal output of three popular NN-based methods for detecting phase transitions which rely on solving classification and regression tasks using supervised learning at their core [1]. |
Julian Arnold; Frank Schäfer; |
| 141 | Machine Learning Phases of Matter: Scalability and Limitations Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a scalable machine learning (ML) framework for distinguishing phases and identifying phase transitions in many-body systems. |
Zhongzheng Tian; Sheng Zhang; Gia-Wei Chern; |
| 142 | Learning Together: Training Interatomic Potentials to Multiple Datasets Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, using the information from different datasets together remains a challenge due to the varying levels of theory employed. In this talk, we show that techniques can be used to fit an interatomic potential to multiple organic molecule datasets and that this yields ML potentials with improved accuracies for a variety of tasks. |
Alice Allen; |
| 143 | Local Force Field of Thermally Displaced Atoms in Unstable Bcc Iron from Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: A dataset of energy versus atomic thermal displacements was created from density functional theory molecular dynamics simulations of non-spin-polarized body-centered cubic iron at … |
Adrian De la Rocha Galán; Valeria Arteaga Muniz; Blaise Ayirizia; Sofia Gomez; Ramon Ravelo; Wibe de Jong; Jorge Munoz; |
| 144 | CHGNet: Pretrained Neural Network Potential for Fast and Accurate Charge-constrained Molecular Dynamics Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we present the Crystal Hamiltonian Graph Neural Network (CHGNet) as a novel approach that uses a graph neural network (GNN) based force field to model a universal potential energy surface that can describe both atoms and electrons. |
Bowen Deng; Peichen Zhong; Gerbrand Ceder; |
| 145 | Neural-network-based Interatomic Potential: A Case Study on Lithium Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we will show a general scheme that can be used to develop a neural-network-based interatomic potential using our in-house developed python atom-centered machine learning force field package (PyAMFF) with GPU capabilities. |
Naman Katyal; |
| 146 | On-the-fly Machine Learning-Accelerated Geometry Optimization: Theoretical Screening of A Single Atom Alloy for CO2 Electroreduction Reaction Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we show a mathematical modeling package of training potential energy surfaces using artificial neural networks and applying the machine-learned models to accelerate geometry optimization process. |
Jiyoung Lee; |
| 147 | Investigating The Influence of Local Composition on Properties in Complex Alloys Using Machine Learned Interatomic Potentials Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this presentation, we will discuss our group’s progress in addressing both challenges. |
Megan McCarthy; Jacob Startt; Remi Dingreville; Aidan Thompson; Mitchell Wood; |
| 148 | Nanoparticle Heterogeneous Catalysis Dynamics Simulations with Machine Learned Force Fields Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We train a collection of robust, Bayesian machine learned force fields (MLFFs) using the FLARE on-the-fly active learning framework implemented using Gaussian Process regression. |
Cameron Owen; Yu Xie; Jin Soo Lim; Boris Kozinsky; |
| 149 | Melting and Phase Separation of SiC from Large-scale Machine Learning Molecular Dynamics Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we use Bayesian active learning to train a machine learning potential for SiC at a wide range of temperatures and pressures, and observe the phase decomposition process into Si and C-rich phases in both the active learning and the large-scale MD stages. |
Yu Xie; Senja Ramakers; Boris Kozinsky; |
| 150 | ML Models for Partition Functions: from The Prediction of Thermodynamic Properties to The Exploration of Transition Pathways Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We demonstrate the accuracy and reliability of the ML models by showing the ability of the ML-partition function to predict thermodynamic properties for single component-systems, mixtures, confined fluids. |
Jerome Delhommelle; Caroline Desgranges; |
| 151 | Diffeomorphisms Invariance Is A Proxy of Performance in Deep Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: It has been proposed that they do so by becoming stable to diffeomorphisms, yet existing empirical measurements support that it is often not the case. We revisit this question by defining a maximum-entropy distribution on diffeomorphisms, that allows to study typical diffeomorphisms of a given norm. |
Leonardo Petrini; Alessandro Favero; Mario Geiger; Matthieu Wyart; |
| 152 | Predicting Phase Preferences of Transition Metal Dichalcogenides Using Machine Learning Techniques Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, I will discuss our recent work [Phys. |
Pratibha Dev; Pankaj Kumar; Sharmila Shirodkar; Vinit Sharma; |
| 153 | Surface Doping of MoO3-x on Hydrogenated Diamond Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We performed reactive molecular dynamics simulations to study the deposition of MoO 3-x on hydrogenated diamond (111) surface and used first-principles calculations based on density functional theory to investigate the change transfer and electronic structures. |
Liqiu Yang; Thomas Linker; Aravind Krishnamoorthy; Ken-ichi Nomura; Rajiv Kalia; Aiichiro Nakano; Priya Vashishta; |
| 154 | Supercharging Semi-empirical Quantum Chemistry with Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we present an extended SEQC formalism dynamically parametrized via ML. |
Martin Stoehr; Todd Martinez; |
| 155 | Efficient Calculation of Χ Parameters for Polymer Interactions from Simulation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we present impacts of chain length on estimates of the χ parameter from atomistic simulations. |
Kevin Shen; Glenn Fredrickson; M. Scott Shell; My Nguyen; Charles Li; Dan Sun; Nick Sherck; Paul Irving; Venkatraghavan Ganesan; |
| 156 | First-principles Path-integral Molecular Dynamics Study of Ferroelectricity and Isotope Effects in KDP Crystals with Deep Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We study the ferroelectric phase transition of KDP and DKDP with all-atom path-integral molecular dynamics (PIMD) based on a neural network potential energy model trained on density functional theory with SCAN approximation. |
Bingjia Yang; Pinchen Xie; Roberto Car; |
| 157 | Sobolev Sampling of Free Energy Landscapes Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present a family of fast sampling methods for classical and first principle molecular simulations of systems having rugged free energy landscapes. |
Pablo Zubieta; Juan De Pablo; |
| 158 | Modified Metal-assisted Exfoliation for Low Disorder, Large Monolayer Devices Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we report a facile modified metal-assisted mechanical exfoliation method to produce high quality 2D material monolayer arrays on bare Si chip without exposing to water or solution based etching process. |
Yangchen He; Daniel Rhodes; |
| 159 | Towards Learning A Lattice Boltzmann Collisional Operator Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present preliminary results in which a neural network is successfully trained as a surrogate of the single relaxation time BGK operator. |
Alessandro Gabbana; Alessandro Corbetta; Vitaliy Gyrya; Daniel Livescu; Joost Prins; Federico Toschi; |
| 160 | Learning Closure Models with Neural Operator-embedded Differentiable CFD Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We discuss an approach using the differentiable physics paradigm that combines known physics with machine learning to develop closure models for the Navier-Stokes equations. |
Varun Shankar; Venkat Viswanathan; |
| 161 | A Data-free Partial Differential Equation (PDE) Solver in The Framework of Physics-informed Neural Networks (PINN) Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, combining the advantages of finite difference method (FDM) and PINN, a new data-free PDE solver called PINN-FDM is introduced. |
Xiaoyu Tang; Boqian Yan; |
| 162 | Defending Smart Electrical Power Grids Against Cyberattacks with Deep Q-learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We demonstrate the workings of our deep-Q learning solution using the benchmark W&W 6-bus and the IEEE 30-bus systems, the latter being a relatively large-scale power-grid system that defies the conventional Q-learning approach. |
Mohammadamin Moradi; Ying-Cheng Lai; Yang Weng; |
| 163 | Using Transfer Learning to Generate Samples for Large Systems of The Spin-fermion Hamiltonian Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: The main bottleneck of our previous work is generating the training data set requires time and memory resources that scale unfavorably as the sytem’s size. We present a transfer learning approach in which we train neural networks on smaller systems and by appropriately modifying them we build models that can generate samples for far larger systems. |
Georgios Stratis; Pau Closas; Adrian Feiguin; |
| 164 | Learning Coronal Nonlinear Force-Free Magnetic Fields Through Differentiable Rendering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We consider the ill-posed problem of computing the 3D magnetic field above the surface of the sun (the corona) from the vector magnetic field on the surface (the photosphere) and 2D optical projections of plasma flowing through magnetic field lines in the corona. |
Phillip Lo; Eric Jonas; |
| 165 | Multiscale Perturbed Gradient Descent: Chaotic Regularization and Heavy-Tailed Limits Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, we introduce multiscale perturbed GD (MPGD), a novel optimization framework where the GD recursion is augmented with chaotic perturbations that evolve via an independent dynamical system. |
Soon Hoe Lim; |
| 166 | Data-driven Discovery and Interpolation of Green’s Functions Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To gain a deeper understanding of nature, we present a data-driven approach to mathematically model unknown physical systems, by learning a Green’s function for its hidden, governing partial differential equations. |
Harshwardhan Praveen; Nicolas Boulle; Christopher Earls; |
| 167 | Toward Automated Design of Optimized High Energy Density Material Science Experiments on The Z Machine Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: A computational framework has been developed that analyses the statistical spread in LTGS timings to calculate the probability of experiment failure. |
Andrew Porwitzky; Justin Brown; William Lewis; |
| 168 | Using Deep-learning to Uncover Physics of Magnetic (charged Particle) Confinement in Magnetized Liner Inertial Fusion Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We built an artificial neural network surrogate trained on expensive physics calculations of magnetized fast charged-particle transport and associated secondary neutron emission in MIF plasmas used to diagnose BR. |
William Lewis; Owen Mannion; Christopher Jennings; Daniel Ruiz; Patrick Knapp; Matthew Gomez; Adam Harvey-Thompson; Stephen Slutz; Kristian Beckwith; Kristian Beckwith; |
| 169 | MADEM: Energy-efficient Training of Deep Neural Networks Using Memristor Arrays Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: By using a novel learning algorithm compatible with analog in-memory-computing provided by memristor array, we demonstrate efficient training of deep neural networks, which is not only biologically plausible (local update rule), but also energy-efficient (5 orders of magnitude smaller), and faster (36 smaller latency). |
Suin Yi; Suhas Kumar; |
| 170 | Automatic Detection of Fake Tweets About Covid-19 Vaccine in Portuguese Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We developed BERTVacPort, an approach to automatically and reliably label tweets about vaccines in Portuguese as reliable or fake. |
Rafael Geurgas Zavarizz; Leandro Tessler; |
| 171 | Transferable Coarse Grained Free Energy Models Enabled By Active Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work helps pave the way towards efficient autonomous training of reliable and uncertainty aware many-body machine learned coarse grain models. |
Blake Duschatko; Jonathan Vandermause; Nicola Molinari; Boris Kozinsky; |
| 172 | Data-driven Subcomponent Design and Engineering Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In the first part of this talk, we will present various case studies, such as a multi-faceted high-throughput screening method, a query-based method utilizing material databases, and a descriptor-based materials design. |
Soo Kim; Muratahan Aykol; |
| 173 | It’s All About That Bayes: Data-driven Insights Into Energy Devices Without The Black Box Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, I will showcase prior and ongoing work in using Bayesian parameter estimation to extract unprecedented materials-level insights from simple, automated electrical characterization of photovoltaic devices. |
Rachel Kurchin; |
| 174 | The Materials Experiment Knowledge Graph Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We characterize the scalability of this approach, especially with respect to executing queries, illustrating the value that modern graph databases can provide to the enterprise of data-driven materials science. |
John Gregoire; Brian Rohr; Michael Statt; Santosh Suram; |
| 175 | Accelerating Energy Materials Discovery in Practice Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, I review difficulties in benchmarking and achieving acceleration, and highlight our research aimed at predicting synthesis, making simulation more efficient, and developing new representations of materials. |
Linda Hung; |
| 176 | Quantum Neural Networks for Medical Image Analysis Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: Medical image analysis has benefited enormously from the rise of deep learning and increasing accuracy of neural network models to classify and segment images. The problem is … |
Yun Li; |
| 177 | Current Challenges for Data Science and Trustworthy AI in Industry and Government Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: The rapid development and adoption of AI has major ramifications for industry and government. AI is an increasing factor and component of national and economic development, … |
J.P. Auffret; |
| 178 | Data Science in Retail: Pricing Optimization and Customer Engagement Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Such multi-objective optimization for a wide range of products is a computationally intensive task. We propose a two-level approach to this problem. |
Aleksey Kocherzhenko; |
| 179 | Learning Accurate Closures of A Kinetic Theory of An Active Fluid Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we present a learning framework that relies on invariant representation of tensor-valued isotropic functions to learn the closure models directly from kinetic simulations. |
Suryanarayana Maddu; Scott Weady; Michael Shelley; |
| 180 | Data-driven Approaches to Predict and Understand The Dynamics of Active Nematics Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: However, developing models using traditional statistical physics approaches is challenging because active materials lack the scale separation characteristic of equilibrium systems. In this presentation, I will discuss efforts to use data-driven techniques to address this challenge in the context of a model active material, microtubule-based active nematics. |
Michael Hagan; |
| 181 | Directing Assembly and Encoding Information in Active Matter Via Light Patterns Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, using simulations and data science, we unravel the interplay between the properties of the active particles and the features of the light pattern, 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 following the application of the light pattern. |
Jerome Delhommelle; Caroline Desgranges; |
| 182 | Learning A Compact Representation of The Nematic Director of Active Nematics Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work, we develop a neural network to learn a compact (reduced-dimension) representation of the Q-tensor field that describes the nematic director of experimental active nematics. |
Phu Tran; Zvonimir Dogic; Aparna Baskaran; Pengyu Hong; Michael Hagan; |
| 183 | Categorizing Spatiotemporal Dynamics of Bacterial Swarm Fronts Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we reduce the complex dynamics of the multicellular system to the time evolution of closed curves by representing the swarms by their moving boundary. |
Alasdair Hastewell; Hannah Jeckel; Andreea-Oana Chelban; Gabriel Rodriguez-Roig; Knut Drescher; Jorn Dunkel; |
| 184 | Predicting Spatio-temporal Patterns of Cells Guided By Time-varying Guidance Cues with Reservoir Computing Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This problem is further exacerbated when the training data is short in time and includes a stochastic component. We therefore propose a reservoir computer architecture with an additional input vector that mimics the temporal dynamics of a parameter of the dynamical system. |
Hoony Kang; Keshav Srinivasan; Michelle Girvan; Wolfgang Losert; |
| 185 | Rapid Detection and Classification of Motile Cell Tracks in 3D Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We use DHM data as ground truth libraries for a deep learning object detection network. |
Samuel Matthews; Laurence Wilson; James Walker; Victoria Hodge; |
| 186 | Neural Networks for Data-driven Models of Cell Mechanics Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we show how machine learning can link protein distributions to mechanical forces, leading to data-driven physical models without requiring knowledge at the microscale. |
Matthew Schmitt; Jonathan Colen; Stefano Sala; Margaret Gardel; Patrick Oakes; Vincenzo Vitelli; |
| 187 | Correcting Optical Wavefront Distortion Due to Strong Atmospheric Turbulence Using Deep Neural Networks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here, we propose a novel convolutional neural network model to efficiently and accurately perform Zernike decomposition of optical wavefront distortion up to 12 Zernike modes. |
Paramott Bunnjaweht; Poompong Chaiwongkhot; Thiparat Chotibut; |
| 188 | Maximum Entropy for Fine-tuning Quantum Dot Arrays Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our work is an important step in establishing reliable fine-tuning methods for calibrating quantum dots to work as qubits. |
Mick Ramsey; Florian Luthi; Rostyslav Savytskyy; Stephanie Bojarski; Justyna Zwolak; |
| 189 | Agile Experiment Management Software Designed for Large Scale Quantum System Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this work I present a compromised solution NLab (Not bloated Laboratory), that allows the user to focus on details of experiments and break free some of the human factor barriers. |
Orkesh Nurbolat; |
| 190 | Computational Study of Mixing Solid Materials for CO2 Capture Technology Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this presentation, the results of M 2O/Al 2O 3 (M=Li, Na, K) mixtures (MAlO 2 and M 5AlO 4) capturing CO 2 will be demonstrated in detail. |
Yuhua Duan; |
| 191 | Leveraging Interpretable Machine Learning for Climate Physics Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this presentation, I will describe the complex and multiscale nature of the climate system and how machine learning can be leveraged to deepen our understanding of key physical climate processes. |
Laure Zanna; Andrew Ross; Pavel Perezhogin; Carlos Fernandez-Granda; Ziwei Li; |
| 192 | Probabilistic Learning for Predictive Modeling of Climate Variability Related Papers Related Patents Related Grants Related Venues Related Experts View Abstract: While comprehensive climate models are skilful at predicting the response of the climate system to external forcing, they are less skilful when it comes to predicting the natural … |
Balu Nadiga; |
| 193 | Learning Fire Spread Dynamics with Physics-constrained Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this talk, I will present preliminary results from a physics-constrained machine learning (ML) model of fire spread dynamics. |
Jatan Buch; Aniket Jivani; Xun Huan; A. Park Williams; Pierre Gentine; |
| 194 | Long-term Instability of Deep Learning-based Digital Twins of The Climate System: Cause and Solution Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We show improvement in short-term forecasts, as well as long-term stable emulations for hundreds of years with accurate mean and variability. |
Ashesh Chattopadhyay; Pedram Hassanzadeh; |
| 195 | Global and Direct Solar Irradiance Estimation Using Deep Learning and Selected Spectral Satellite Images Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: As for DNI estimation, the proposed method shows a nRMSE reduction of 13.77%. |
Shanlin Chen; |
| 196 | Integrating The Spectral Analyses of Neural Networks and Climate Physics for Stable, Explainable, and Generalizable Models Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Using several setups of 2D turbulence, two-layer quasi-geostrophic turbulence, Rayleigh-Benard convection, and ERA5 reanalysis, we introduce methods to address (1)-(4). |
Pedram Hassanzadeh; Yifei Guan; Adam Subel; Ashesh Chattopadhyay; |
| 197 | Reduced-order Modeling of Arctic Amplification Feedbacks Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we present initial work on data-driven reduced-order models to analyze the key feedback between ice albedo and surface temperature. |
Adam Rupe; Craig Bakker; Derek DeSantis; Jian Lu; |
| 198 | Physics-informed and Equality-constrained Artificial Neural Networks with Applications to Partial Differential Equations and Multi-fidelity Data Assimilation Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this study, we investigate the application of artificial neural networks to mining physics. |
shamsulhaq basir; Inanc Senocak; |
| 199 | Energy Harvesting By An Intelligent Body from Turbulence Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Here we report numerical and analytical evidence on how the rotational dynamics of a neutrally buoyant body can conspire to allow the harvesting of energy from the turbulent fluid motion efficiently. |
Yagmur Kati; sinan gundogdu; Bruno Andreis; Sabine Klapp; |
| 200 | Numerical Proof of Shell Model Turbulence Closure Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This work demonstrates the capability of Machine Learning to capture complex multiscale dynamics and reproduce complex multi-scale and multi-time non-gaussian behaviors, opening up the possibility to tackle turbulence modelling in Navier-Stokes Equations. |
Giulio Ortali; Alessandro Corbetta; Gianluigi Rozza; Federico Toschi; |
| 201 | Enabling AI for Open Science on Supercomputers at NERSC Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: This presentation will describe our vision at NERSC for enabling and supporting cutting-edge scientific AI through advanced HPC system deployments, research engagements, benchmark challenges and datasets, and outreach. |
Steven Farrell; |
| 202 | Facilitating Open Science Practices at User Facility Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We will describe a data management framework deployed at the National High Magnetic Field Laboratory (NHMFL/MagLab) in collaboration with the Los Alamos National Laboratory (LANL) Research Library Prototyping team. |
Lyudmila Balakireva; Fedor Balakirev; |
| 203 | Application of Causality-first Functional Decomposition Trees to Data Science and Materials Informatics Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: In this presentation, examples of conceptual structure creation using the functional decomposition trees will be presented, which facilitate explanation and modification of hierarchical structures outside the domain by directly associating vocabulary with functions. |
Hiori Kino; |
| 204 | A Dynamics Data Set for Spin Ice Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: We present the results of our analysis which implements both traditional and data-driven methods. |
Kyle Sherman; Michael Lawler; |
| 205 | Novel Representations and Quantitative Structure Property Relationships for Polymers Using Machine Learning Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To create computationally efficient models, we developed novel representations of polymers that simplify yet retain the molecular structure. |
Javad Tamnanloo; Everen Wegner; Abraham Joy; Mesfin Tsige; |
| 206 | Application of GARCH Models Generalized with Machine Learning and Quantum Statistical Physics Methodology in Exotic Financial Data and Beyond Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: Our new approach is then tested in simulated data using Monte Carlo and bootstrap methods, as well as real data from the secondary financial markets, the disease infection records, and climate change patterns. |
Haidong Yan; |
| 207 | NexusLIMS: A Laboratory Information Management System for Shared-Use Electron Microscopy Facilities Related Papers Related Patents Related Grants Related Venues Related Experts View Highlight: To capture microscopy data consistent with the FAIR data principles, we built NexusLIMS, a laboratory information management system managing microscopy output across two NIST campuses. |
June Lau; |