An STDP-Based Supervised Learning Algorithm for Spiking Neural Networks

TL;DR

This paper introduces a supervised learning algorithm for hierarchical Spiking Neural Networks using STDP, achieving classification accuracy comparable to traditional neural networks on MNIST.

Contribution

It presents a novel STDP-based supervised learning method for SNNs with a specific time window mechanism, bridging biological plausibility and practical performance.

Findings

Achieves MNIST classification accuracy close to MLPs.

Uses a time window for STDP updates based on presynaptic spikes.

Demonstrates the viability of supervised learning in SNNs.

Abstract

Compared with rate-based artificial neural networks, Spiking Neural Networks (SNN) provide a more biological plausible model for the brain. But how they perform supervised learning remains elusive. Inspired by recent works of Bengio et al., we propose a supervised learning algorithm based on Spike-Timing Dependent Plasticity (STDP) for a hierarchical SNN consisting of Leaky Integrate-and-fire (LIF) neurons. A time window is designed for the presynaptic neuron and only the spikes in this window take part in the STDP updating process. The model is trained on the MNIST dataset. The classification accuracy approach that of a Multilayer Perceptron (MLP) with similar architecture trained by the standard back-propagation algorithm.