Explainable spiking neural network for real time feature classification

Abstract

ABSTRACT The work presents a concept of an implementation of an explainable artificial intelligence (XAI) using effective models of third-generation neurons. The article discusses a concept of building a neural network based on spiking neurons modelled on ladder nervous systems. A distinction is made between voltage signals encoding information in a network and current signals which contain the correlation between information in the network and pattern features. Analyzes feature a neuron model based on the cusp catastrophe theory eliminating network sensitivity to problems of synapse plasticity, weight mismatch and coupling of neurons based on electric models. The paper presents applications of a spiking neural network for reporting the state of water quality while generating justifications. The article contains results of an analysis of confusion of justifications with ACC = 1 for a set of 10,000 patterns. It also discusses the speed of pattern analysis in the simulated network.