EUVIMEDEUVIMED entdecken
Crossref

Frequency Propagation: Multimechanism Learning in Nonlinear Physical Networks

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

Neural Computation · 21.03.2024 · 36 (4) · 596-620

DOI: 10.1162/neco_a_01648 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Neural Computation, online erschienen am 21.03.2024. Verfasst von Vidyesh Rao Anisetti und 3 weiteren Autor:innen. Beteiligte Einrichtung: Physics Department, Syracuse University, Syracuse, NY 13244 U.S.A. vvaniset@syr.edu. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 31 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 frequency. 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 instance 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 independent 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.

Autor:innen und Institutionen

  • Physics Department, Syracuse University, Syracuse, NY 13244 U.S.A. vvaniset@syr.edu.
  • Department of Physics, University of Florida, Gainesville, FL 32611, U.S.A. an.kandala@ufl.edu.
  • Department of Mathematics, ETH Zürich, 8092 Zürich, Switzerland benjamin.scellier@polytechnique.edu.
  • Physics Department, Syracuse University, Syracuse, NY 13244 U.S.A.
  • Indian Creek Farm, Ithaca, NY 14850, U.S.A. jmschw02@syr.edu.

Zitieren

APA

Anisetti, V. R., Kandala, A., Scellier, B., & Schwarz, J. M. (2024). Frequency Propagation: Multimechanism Learning in Nonlinear Physical Networks. Neural Computation, 36(4), 596-620. https://doi.org/10.1162/neco_a_01648

Vancouver

Anisetti VR, Kandala A, Scellier B, Schwarz JM. Frequency Propagation: Multimechanism Learning in Nonlinear Physical Networks. Neural Computation. 2024;36(4):596-620. doi:10.1162/neco_a_01648

BibTeX
@article{Anisetti2024,
  author = {Anisetti, Vidyesh Rao and Kandala, Ananth and Scellier, Benjamin and Schwarz, J M},
  title = {Frequency Propagation: Multimechanism Learning in Nonlinear Physical Networks},
  journal = {Neural Computation},
  year = {2024},
  volume = {36},
  number = {4},
  pages = {596--620},
  doi = {10.1162/neco_a_01648}
}
Kostenlos starten →