APS Logo

Physics of Learning I: Natural systems

FOCUS · A03 · ID: 46150

Presentations

  • A mathematical analysis of learning in both biological and artificial neural networks

    ORAL · Invited

    –

    Publication: M. Advani and S. Ganguli, Statistical mechanics of optimal convex inference in high dimensions, Physical Review X, 2016.<br><br>A.K. Lampinen and S. Ganguli, An analytic theory of generalization dynamics and transfer learning in deep linear networks, International Conference on Learning Representations (ICLR), 2019.<br><br>A. Saxe, J. McClelland, S. Ganguli, A. Saxe, J. McClelland, S. Ganguli, Exact solutions to the nonlinear dynamics of learning in deep neural networks, PNAS 2019. <br><br>Y. Bahri, J. Kadmon, J. Pennington, S. Schoenholz, J. Sohl-Dickstein, and S. Ganguli, Statistical mechanics of deep learning, Annual Reviews of Condensed Matter Physics, 2020.

    Presenters

    • Surya Ganguli

      Stanford, Stanford University

    Authors

    • Surya Ganguli

      Stanford, Stanford University

    View abstract →

  • Desynchronous and decentralized learning In a physical network

    ORAL

    –

    Presenters

    • Jacob F Wycoff

      University of Pennsylvania

    Authors

    • Jacob F Wycoff

      University of Pennsylvania

    • Sam J Dillavou

      University of Pennsylvania

    • Menachem Stern

      University of Pennsylvania

    • Andrea J Liu

      University of Pennsylvania

    • Douglas J Durian

      University of Pennsylvania

    View abstract →

  • Merging Kalman Filtering with the information bottleneck technique for optimal state inference

    ORAL

    –

    Presenters

    • Vedant Sachdeva

      University of Chicago

    Authors

    • Vedant Sachdeva

      University of Chicago

    • Thierry Mora

      CNRS - Sorbonne University, Ecole Normale Superieure, Laboratoire de physique de l'Ecole normale superieure, CNRS, Laboratoire de physique de l'École normale supérieure

    • Arvind Murugan

      University of Chicago

    • Stephanie E Palmer

      University of Chicago

    • Aleksandra M Walczak

      Ecole Normale Superieure, CNRS - Sorbonne University

    View abstract →

  • A theory of weight distribution-constrained learning

    ORAL

    –

    Presenters

    • Weishun Zhong

      Massachusetts Institute of Technology

    Authors

    • Weishun Zhong

      Massachusetts Institute of Technology

    • Ben Sorscher

      Stanford University

    • Daniel D Lee

      Cornell Tech

    • Haim I Sompolinsky

      The Hebrew University of Jerusalem and Harvard University, Hebrew University of Jerusalem, Center for Brain Science, Harvard Univer

    View abstract →

  • Learning in gene regulatory networks: dimensionality reduction by master regulators

    ORAL

    –

    Publication: H. Schreier, Y. Soen and N. Brenner, "Adaptation by drive reduction in large random networks", Nature Communications 8, 14826 (2017).<br>A. Rivkind, H. Schreier, N. Brenner and O. Barak, "Scale free topology as an effective feedback system". PLoS Comp. Biol. 16, e1007825 (2020).

    Presenters

    • Naama Brenner

      Technion Israel Institute of Technology, Technion - Israel Institute of Technolog

    Authors

    • Naama Brenner

      Technion Israel Institute of Technology, Technion - Israel Institute of Technolog

    View abstract →

  • Memory formation in adaptive networks

    ORAL

    –

    Publication: Bhattacharyya, Zwicker, Alim PRL (under review)

    Presenters

    • Komal Bhattacharyya

      MPI for Dynamics and Self-organisation

    Authors

    • Komal Bhattacharyya

      MPI for Dynamics and Self-organisation

    • David Zwicker

      MPI for Dynamics and Self-organisation

    • Karen Alim

      TUM, TU Munich

    View abstract →

  • The route to chaos of reinforcement learning in routing networks

    ORAL

    –

    Publication: Bielawski, J. et. al. Follow-the-Regularized-Leader Routes to Chaos in Routing Games, ICML 2021 (https://arxiv.org/abs/2102.07974)<br>Chotibut, T. et. al. The route to chaos in routing games: When is price of anarchy too optimistic?, NeurIPS 2020 (https://arxiv.org/abs/1906.02486)

    Presenters

    • Thiparat Chotibut

      Chula Intelligent and Complex Systems Lab, Department of Physics, Chulalongkorn University, Thailand, Chula Intelligent and Complex Systems Lab, Department of Physics, Faculty of Science, Chulalongkorn University, Bangkok, Thailand, Chula Intelligent and Complex Systems Lab, Department of Physics, Faculty of Science, Chulalongkorn University, Thailand

    Authors

    • Jakub Bielawski

      Department of Mathematics, Cracow University of Economics, Poland

    • Thiparat Chotibut

      Chula Intelligent and Complex Systems Lab, Department of Physics, Chulalongkorn University, Thailand, Chula Intelligent and Complex Systems Lab, Department of Physics, Faculty of Science, Chulalongkorn University, Bangkok, Thailand, Chula Intelligent and Complex Systems Lab, Department of Physics, Faculty of Science, Chulalongkorn University, Thailand

    • Fryderyk Falniowski

      Department of Mathematics, Cracow University of Economics, Poland

    • Michal Misiurewicz

      Department of Mathematical Sciences, Indiana University-Purdue University Indianapolis, USA

    • Georgios Piliouras

      Engineering Systems and Design, Singapore University of Technology and Design, Singapore

    View abstract →