Deep Unsupervised Learning Using Spike-Timing-Dependent Plasticity

TL;DR

This paper introduces a deep learning framework using Spike-Timing-Dependent Plasticity (STDP) for unsupervised training of neural networks, achieving improved accuracy and faster convergence on image classification tasks.

Contribution

The work presents a novel Deep-STDP method that enables scalable, deep unsupervised learning in spiking neural networks with competitive performance.

Findings

Achieved 24.56% higher accuracy on Tiny ImageNet subset.

Converged 3.5 times faster at the same accuracy.

Demonstrated scalability of STDP-based learning in deep networks.

Abstract

Spike-Timing-Dependent Plasticity (STDP) is an unsupervised learning mechanism for Spiking Neural Networks (SNNs) that has received significant attention from the neuromorphic hardware community. However, scaling such local learning techniques to deeper networks and large-scale tasks has remained elusive. In this work, we investigate a Deep-STDP framework where a rate-based convolutional network, that can be deployed in a neuromorphic setting, is trained in tandem with pseudo-labels generated by the STDP clustering process on the network outputs. We achieve $24.56\%$ higher accuracy and $3.5\times$ faster convergence speed at iso-accuracy on a 10-class subset of the Tiny ImageNet dataset in contrast to a $k$-means clustering approach.