LGDIS-NNDec 22, 2023

A universal approximation theorem for nonlinear resistive networks

arXiv:2312.15063v35 citationsh-index: 16Phys Rev Appl
Originality Incremental advance
AI Analysis

This work provides a foundational result for developing universal self-learning electrical networks, which could impact analog computing platforms in machine learning.

The paper tackles the problem of determining the computational capabilities of nonlinear resistive networks for machine learning, proving that networks with voltage sources, linear resistors, diodes, and voltage-controlled voltage sources can approximate any continuous function to arbitrary precision under ideal assumptions.

Resistor networks have recently been studied as analog computing platforms for machine learning, particularly due to their compatibility with the Equilibrium Propagation training framework. In this work, we explore the computational capabilities of these networks. We prove that electrical networks consisting of voltage sources, linear resistors, diodes, and voltage-controlled voltage sources (VCVSs) can approximate any continuous function to arbitrary precision. Central to our proof is a method for translating a neural network with rectified linear units into an approximately equivalent electrical network comprising these four elements. Our proof relies on two assumptions: (a) that circuit elements are ideal, and (b) that variable resistor conductances and VCVS amplification factors can take any value (arbitrarily small or large). Our findings provide insights that could guide the development of universal self-learning electrical networks.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes