Frequency Propagation: Multimechanism Learning in Nonlinear Physical Networks

Vidyesh Rao Anisetti, Ananth Kandala, Benjamin Scellier, J. M. Schwarz

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

We introduce frequency propagation, a learning algorithm for nonlinear physical networks. In a resistive electrical circuit with variable resistors, an activation current is applied at a set of input nodes at one frequency and an error current is applied at a set of output nodes at another fre-quency. The voltage response of the circuit to these boundary currents is the superposition of an activation signal and an error signal whose coefficients can be read in different frequencies of the frequency domain. Each conductance is updated proportionally to the product of the two coefficients. The learning rule is local and proved to perform gradient descent on a loss function. We argue that frequency propagation is an in-stance of a multimechanism learning strategy for physical networks, be it resistive, elastic, or flow networks. Multimechanism learning strategies incorporate at least two physical quantities, potentially governed by in-dependent physical mechanisms, to act as activation and error signals in the training process. Locally available information about these two signals is then used to update the trainable parameters to perform gradient descent. We demonstrate how earlier work implementing learning via chemical signaling in flow networks (Anisetti, Scellier, et al., 2023) also falls under the rubric of multimechanism learning.

Original languageEnglish (US)
Pages (from-to)596-620
Number of pages25
JournalNeural Computation
Volume36
Issue number4
DOIs
StatePublished - Mar 21 2024

ASJC Scopus subject areas

  • Arts and Humanities (miscellaneous)
  • Cognitive Neuroscience

Fingerprint

Dive into the research topics of 'Frequency Propagation: Multimechanism Learning in Nonlinear Physical Networks'. Together they form a unique fingerprint.

Cite this