Application of a Compartmental Spiking Neuron Model with Structural Adaptation for Solving Classification Problems

Abstract

The problem of classification using a compartmental spiking neuron model is considered. The state of the art of spiking neural networks analysis is carried out. It is concluded that there are very few works on the study of compartmental neuron models. The choice of a compartmental spiking model is justified as a neuron model for this work. A brief description of such a model is given, and its main features are noted in terms of the possibility of its structural reconfiguration. The method of structural adaptation of the model to the input spike pattern is described. The general scheme of the compartmental spiking neurons’ organization into a network for solving the classification problem is given. The time-to-first-spike method is chosen for encoding numerical information into spike patterns, and a formula is given for calculating the delays of individual signals in the spike pattern when encoding information. Brief results of experiments on solving the classification problem on publicly available data sets (Iris, MNIST) are presented. The conclusion is made about the comparability of the obtained results with the existing classical methods. In addition, a detailed step-by-step description of experiments to determine the state of an autonomous uninhabited underwater vehicle is provided. Estimates of computational costs for solving the classification problem using a compartmental spiking neuron model are given. The conclusion is made about the prospects of using spiking compartmental models of a neuron to increase the bio-plausibility of the implementation of behavioral functions in neuromorphic control systems. Further promising directions for the development of neuromorphic systems based on the compartmental spiking neuron model are considered.

The incremental learning algorithm for compartmental spiking neuron model

“…CSMN is used in neural networks or other models, where, after learning the CSMN for a given spiking pattern, the neuron model is able, with some error, to describe the class of patterns to which the given pattern belonged. Spiking patterns are obtained by increasing the dimension by 1 and then encoding the source data using the method described in [6].…”

“…The design of the neuron model allows training of neural networks built on it, both by changing the network topology and at the level of structures of individual neurons. Architectures of neural networks built on CSMN have been developed that allow solving the classification problem on a small training set [6]. However, the existing CSMN structural learning algorithm [7] allows the model to be used only in an offline scenario, since the algorithm assumes changing the neuron structure only by increasing the number of compartments, and learning itself is assumed only once during the entire time the model is used.…”