APS Logo

Learning in Physical Systems without Neurons

FOCUS · D07 · ID: 1067740

Presentations

  • Equilibrium Propagation: A Physics-Grounded Theory of Computation and Learning

    ORAL · Invited

    –

    Publication: Equilibrium propagation: bridging the gap between energy-based models and backpropagation<br>Training end-to-end analog neural networks with equilibrium propagation<br>A deep learning theory for neural networks grounded in physics<br>Agnostic physics-driven deep learning<br>Frequency propagation: multi-mechanism learning in nonlinear physical networks<br>A universal approximation theorem for deep resistive networks<br>A fast algorithm to simulate deep resistive networks

    Presenters

    • Benjamin Scellier

      Rain Neuromorphics, ETH Zurich

    Authors

    • Benjamin Scellier

      Rain Neuromorphics, ETH Zurich

    View abstract →

  • Physical learning of energy-efficient solutions

    ORAL

    –

    Publication: Planned paper

    Presenters

    • Menachem Stern

      University of Pennsylvania

    Authors

    • Menachem Stern

      University of Pennsylvania

    • Sam J Dillavou

      University of Pennsylvania

    • Douglas J Durian

      University of Pennsylvania

    • Andrea J Liu

      University of Pennsylvania

    View abstract →

  • Transistor-Based Self-Learning Networks

    ORAL

    –

    Publication: [1] S Dillavou, M Stern, DJ Durian, AJ Liu, Demonstration of Decentralized, Physics-Driven Learning, Physical Review Applied, 18, 014040 (2022) <br>[2] JF Wycoff, S Dillavou, M Stern, AJ Liu, DJ Durian, Learning Without a Global Clock: Asynchronous Learning in a Physics-Driven Learning Network Journal of Chemical Physics, 156, 144903 (2022) <br>[3] M Stern, S Dillavou, MZ Miskin, DJ Durian, AJ Liu, Physical Learning Beyond the Quasistatic Limit, Physical Review Research, 4, L022037 (2022)

    Presenters

    • Sam J Dillavou

      University of Pennsylvania

    Authors

    • Sam J Dillavou

      University of Pennsylvania

    • Benjamin Beyer

      University of Pennsylvania

    • Menachem Stern

      University of Pennsylvania

    • Marc Z Miskin

      University of Pennsylvania

    • Andrea J Liu

      University of Pennsylvania

    • Douglas J Durian

      University of Pennsylvania

    View abstract →

  • Physical learning at nonzero temperatures

    ORAL

    –

    Presenters

    • Jovana Andrejevic

      University of Pennsylvania

    Authors

    • Jovana Andrejevic

      University of Pennsylvania

    • Purba Chatterjee

      University of Pennsylvania

    • Sidney R Nagel

      University of Chicago

    • Andrea J Liu

      University of Pennsylvania

    View abstract →

  • Electrochemical potential enables dormant spores to integrate environmental signals

    ORAL

    –

    Publication: DOI: 10.1126/science.abl7484

    Presenters

    • Leticia Galera-Laporta

      University of California, San Diego, University of California San Diego

    Authors

    • Leticia Galera-Laporta

      University of California, San Diego, University of California San Diego

    • Kaito Kikuchi

      University of California San Diego

    • Colleen Weatherwax

      University of California San Diego

    • Jamie Y Lam

      University of California San Diego

    • Eun Chae Moon

      University of California San Diego

    • Emmanuel A Theodorakis

      University of California San Diego

    • Jordi Garcia-Ojalvo

      Universitat Pompeu Fabra

    • Gürol M Süel

      University of California, San Diego, University of California San Diego

    View abstract →

  • Driving the most marginally stable variables as a paradigm for learning, memory, and optimization

    ORAL

    –

    Publication: [1] Inability of a graph neural network heuristic to outperform greedy algorithms in solving combinatorial optimization problems like Max-Cut, Stefan Boettcher, https://arxiv.org/abs/2210.00623<br>[2] Optimization with Extremal Dynamics, Stefan Boettcher and Allon G. Percus, Phys. Rev. Lett. 86, 5211 (2001), https://journals.aps.org/prl/abstract/10.1103/PhysRevLett.86.5211.

    Presenters

    • Stefan Boettcher

      Emory University

    Authors

    • Stefan Boettcher

      Emory University

    View abstract →

  • Self-learning mechanical circuits

    ORAL

    –

    Presenters

    • Vishal P Patil

      Stanford University

    Authors

    • Vishal P Patil

      Stanford University

    • Ian Ho

      Stanford University

    • Manu Prakash

      Stanford University

    View abstract →