A Spiking Neuron Synaptic Plasticity Model Optimized for Unsupervised Learning

TL;DR

This paper introduces a new synaptic plasticity model tailored for unsupervised learning in spiking neural networks, generalizing STDP, and demonstrates its effectiveness through computer simulations and a novel learning algorithm called SCoBUL.

Contribution

It proposes a novel plasticity model that generalizes STDP for unsupervised learning and integrates it into the SCoBUL algorithm, validated by simulation results.

Findings

Plasticity model effectively generalizes STDP for unsupervised learning.

SCoBUL algorithm demonstrates improved learning efficiency in simulations.

Simulation results confirm the proposed model's suitability for unsupervised learning.

Abstract

Spiking neural networks (SNN) are considered as a perspective basis for performing all kinds of learning tasks - unsupervised, supervised and reinforcement learning. Learning in SNN is implemented through synaptic plasticity - the rules which determine dynamics of synaptic weights depending usually on activity of the pre- and post-synaptic neurons. Diversity of various learning regimes assumes that different forms of synaptic plasticity may be most efficient for, for example, unsupervised and supervised learning, as it is observed in living neurons demonstrating many kinds of deviations from the basic spike timing dependent plasticity (STDP) model. In the present paper, we formulate specific requirements to plasticity rules imposed by unsupervised learning problems and construct a novel plasticity model generalizing STDP and satisfying these requirements. This plasticity model serves as main logical component of the novel supervised learning algorithm called SCoBUL (Spike Correlation Based Unsupervised Learning) proposed in this work. We also present the results of computer simulation experiments confirming efficiency of these synaptic plasticity rules and the algorithm SCoBUL.