Evolutionary features and parameter optimization of spiking neural networks for unsupervised learning

This paper introduces two new hybrid models for clustering problems in which the input features and parameters of a spiking neural network (SNN) are optimized using evolutionary algorithms. We used two novel evolutionary approaches, the quantum-inspired evolutionary algorithm (QIEA) and the optimization by genetic programming (OGP) methods, to develop the quantum binary-real evolving SNN (QbrSNN) and the SNN optimized by genetic programming (SNN-OGP) neuro-evolutionary models, respectively. The proposed models are applied to 8 benchmark datasets, and a significantly higher clustering accuracy compared to a standard SNN without feature and parameter optimization is achieved with fewer iterations. When comparing QbrSNN and SNN-OGP, the former performed slightly better but at the expense of increased computational effort.

I. Introduction

Clustering plays an important role in the machine learning literature [1], [2] and also in real application domains, including market research [3] and medical analysis [4]. As new and more complex applications are developed (high-dimensional and scalable problems), classical techniques, such as k-means, hierarchical clustering, and k-medoids, tend to perform poorly [5]. Therefore, new unsupervised techniques are needed to generate more homogeneous and reliable groups.