Evolving Spiking Neural Networks of artificial creatures using Genetic Algorithm
Document Type
Conference Proceeding
Publication Date
10-31-2016
Publication Title
Proceedings of the International Joint Conference on Neural Networks
Volume
2016-October
First Page
411
Last Page
418
Abstract
This paper presents a Genetic Algorithm (GA) based evolution framework in which Spiking Neural Network (SNN) of single or a colony 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. Inspired by biological neurons, the neuronal connections are considered with different axonal conduction delays. Simulation results prove that the evolutionary algorithm has the capability to find or synthesis artificial creatures which can survive in the environment successfully and also simulations verify that colony approach has a better performance in comparison with a single complex creature.
DOI
10.1109/IJCNN.2016.7727228
ISBN
9781509006199
Recommended Citation
Eskandari, Elahe; Ahmadi, Arash; Gomar, Shaghayegh; Ahmadi, Majid; and Saif, Mehrdad. (2016). Evolving Spiking Neural Networks of artificial creatures using Genetic Algorithm. Proceedings of the International Joint Conference on Neural Networks, 2016-October, 411-418.
https://scholar.uwindsor.ca/electricalengpub/298