Perceptrons from Memristors

TL;DR

This paper introduces memristor-based perceptrons, demonstrating their ability to perform as universal function approximators and paving the way for energy-efficient neural network architectures.

Contribution

It presents the first models of both single and multilayer perceptrons entirely implemented with memristors, adapting learning algorithms accordingly.

Findings

Memristor-based perceptrons perform as expected, satisfying Minsky-Papert's theorem.

Models demonstrate universal approximation capabilities of memristors.

Potential advantages include energy conservation and new paradigms for neural network design.

Abstract

Memristors, resistors with memory whose outputs depend on the history of their inputs, have been used with success in neuromorphic architectures, particularly as synapses and non-volatile memories. However, to the best of our knowledge, no model for a network in which both the synapses and the neurons are implemented using memristors has been proposed so far. In the present work we introduce models for single and multilayer perceptrons based exclusively on memristors. We adapt the delta rule to the memristor-based single-layer perceptron and the backpropagation algorithm to the memristor-based multilayer perceptron. Our results show that both perform as expected for perceptrons, including satisfying Minsky-Papert's theorem. As a consequence of the Universal Approximation Theorem, they also show that memristors are universal function approximators. By using memristors for both the neurons and the synapses, our models pave the way for novel memristor-based neural network architectures and algorithms. A neural network based on memristors could show advantages in terms of energy conservation and open up possibilities for other learning systems to be adapted to a memristor-based paradigm, both in the classical and quantum learning realms.