Contrastive Learning in Memristor-based Neuromorphic Systems

TL;DR

This paper introduces a neuromorphic learning method called contrastive-signal-dependent plasticity (CSDP) for memristor-based systems, enabling simple logic function learning without backpropagation, promising energy-efficient and biologically plausible neural computation.

Contribution

The paper presents a novel contrastive learning approach, CSDP, implemented in memristor-based neuromorphic hardware, avoiding traditional gradient-based methods.

Findings

CSDP can learn simple logic functions in hardware simulations.

The method operates without complex gradient calculations.

It demonstrates potential for energy-efficient neuromorphic learning.

Abstract

Spiking neural networks, the third generation of artificial neural networks, have become an important family of neuron-based models that sidestep many of the key limitations facing modern-day backpropagation-trained deep networks, including their high energy inefficiency and long-criticized biological implausibility. In this work, we design and investigate a proof-of-concept instantiation of contrastive-signal-dependent plasticity (CSDP), a neuromorphic form of forward-forward-based, backpropagation-free learning. Our experimental simulations demonstrate that a hardware implementation of CSDP is capable of learning simple logic functions without the need to resort to complex gradient calculations.