Research reports

Years: 2024 2023 2022 2021 2020 2019 2018 2017 2016 2015 2014 2013 2012 2011 2010 2009 2008 2007 2006 2005 2004 2003 2002 2001 2000 1999 1998 1997 1996 1995 1994 1993 1992 1991

Agnostic Physics-Driven Deep Learning

by B. Scellier and S. Mishra and Y. Bengio and Y. Ollivier

(Report number 2022-26)

Abstract
This work establishes that a physical system can perform statistical learning without gradient computations, via an \emph{Agnostic Equilibrium Propagation} (AEqprop) procedure that combines energy minimization, homeostatic control, and nudging towards the correct response. In AEqprop, the specifics of the system do not have to be known: the procedure is based only on external manipulations, and produces a stochastic gradient descent without explicit gradient computations. Thanks to nudging, the system performs a true, order-one gradient step for each training sample, in contrast with order-zero methods like reinforcement or evolutionary strategies, which rely on trial and error. This procedure considerably widens the range of potential hardware for statistical learning to any system with enough controllable parameters, even if the details of the system are poorly known. AEqprop also establishes that in natural (bio)physical systems, genuine gradient-based statistical learning may result from generic, relatively simple mechanisms, without backpropagation and its requirement for analytic knowledge of partial derivatives.

Keywords: Deep Learning, Equilibrium Propagation, Gradient Computation

@Techreport{SMBO22_1014,
  author = {B. Scellier and S. Mishra and Y. Bengio and Y. Ollivier},
  title = {Agnostic Physics-Driven Deep Learning},
  institution = {Seminar for Applied Mathematics, ETH Z{\"u}rich},
  number = {2022-26},
  address = {Switzerland},
  url = {https://www.sam.math.ethz.ch/sam_reports/reports_final/reports2022/2022-26.pdf },
  year = {2022}
}

Disclaimer
© Copyright for documents on this server remains with the authors. Copies of these documents made by electronic or mechanical means including information storage and retrieval systems, may only be employed for personal use. The administrators respectfully request that authors inform them when any paper is published to avoid copyright infringement. Note that unauthorised copying of copyright material is illegal and may lead to prosecution. Neither the administrators nor the Seminar for Applied Mathematics (SAM) accept any liability in this respect. The most recent version of a SAM report may differ in formatting and style from published journal version. Do reference the published version if possible (see SAM Publications).