Evolving Spiking Neural Networks for Control of Artificial Creatures

Abstract

To understand and analysis behavior of complicated and intelligent organisms, scientists apply bio-inspired concepts including evolution and learning to mathematical models and analyses. Researchers utilize these perceptions in different applications, searching for improved methods and
approaches for modern computational systems. This paper presents a genetic algorithm based evolution framework in which Spiking Neural Network (SNN) of artificial creatures are evolved for higher chance of survival in a virtual environment. The artificial creatures are composed of
randomly connected Izhikevich spiking reservoir neural networks using population activity rate coding. Inspired by biological neurons, the neuronal connections are considered with different axonal conduction delays. Simulations results prove that the evolutionary algorithm has the
capability to find or synthesis artificial creatures which can survive in the environment successfully.