Unsupervised Learning with Self-Organizing Spiking Neural Networks

TL;DR

This paper introduces a hybrid self-organizing spiking neural network that learns in an unsupervised manner, improving classification performance by integrating SOM features with biologically-inspired inhibition strategies.

Contribution

It presents a novel hybrid SNN model combining SOM properties with new inhibition strategies, enhancing unsupervised learning and classification accuracy.

Findings

Improved classification accuracy over existing SNNs.

Effective biologically-inspired inhibition strategies.

Enhanced unsupervised learning of lattice filters.

Abstract

We present a system comprising a hybridization of self-organized map (SOM) properties with spiking neural networks (SNNs) that retain many of the features of SOMs. Networks are trained in an unsupervised manner to learn a self-organized lattice of filters via excitatory-inhibitory interactions among populations of neurons. We develop and test various inhibition strategies, such as growing with inter-neuron distance and two distinct levels of inhibition. The quality of the unsupervised learning algorithm is evaluated using examples with known labels. Several biologically-inspired classification tools are proposed and compared, including population-level confidence rating, and n-grams using spike motif algorithm. Using the optimal choice of parameters, our approach produces improvements over state-of-art spiking neural networks.