The principle of weight divergence facilitation for unsupervised pattern recognition in spiking neural networks

TL;DR

This paper introduces a novel weight divergence facilitation principle for unsupervised pattern recognition in spiking neural networks, inspired by biological synaptic plasticity and signal processing principles.

Contribution

It combines STDP with a physically constrained weight growth rule to enhance signal-to-noise discrimination in neural networks.

Findings

Improved recognition of correlated signals over background noise.

Effective control of synaptic weights based on noise-to-signal ratio.

Demonstrated robustness across various input regimes.

Abstract

Parallels between the signal processing tasks and biological neurons lead to an understanding of the principles of self-organized optimization of input signal recognition. In the present paper, we discuss such similarities among biological and technical systems. We propose adding the well-known STDP synaptic plasticity rule to direct the weight modification towards the state associated with the maximal difference between background noise and correlated signals. We use the principle of physically constrained weight growth as a basis for such weights' modification control. It is proposed that the existence and production of bio-chemical 'substances' needed for plasticity development restrict a biological synaptic straight modification. In this paper, the information about the noise-to-signal ratio controls such a substances' production and storage and drives the neuron's synaptic pressures towards the state with the best signal-to-noise ratio. We consider several experiments with different input signal regimes to understand the functioning of the proposed approach.