Semi-supervised learning combining backpropagation and STDP: STDP enhances learning by backpropagation with a small amount of labeled data in a spiking neural network

TL;DR

This paper introduces a semi-supervised learning approach for spiking neural networks that combines backpropagation with spike-timing-dependent plasticity (STDP), improving accuracy with minimal labeled data and potential for real-time neuromorphic applications.

Contribution

It presents a novel semi-supervised learning method that integrates supervised backpropagation with unsupervised STDP, demonstrating improved accuracy with limited labeled data.

Findings

Enhanced accuracy with small labeled datasets

STDP improves learning beyond self-organization roles

Potential for real-time neuromorphic hardware implementation

Abstract

A semi-supervised learning method for spiking neural networks is proposed. The proposed method consists of supervised learning by backpropagation and subsequent unsupervised learning by spike-timing-dependent plasticity (STDP), which is a biologically plausible learning rule. Numerical experiments show that the proposed method improves the accuracy without additional labeling when a small amount of labeled data is used. This feature has not been achieved by existing semi-supervised learning methods of discriminative models. It is possible to implement the proposed learning method for event-driven systems. Hence, it would be highly efficient in real-time problems if it were implemented on neuromorphic hardware. The results suggest that STDP plays an important role other than self-organization when applied after supervised learning, which differs from the previous method of using STDP as pre-training interpreted as self-organization.