Towards a Biological More Plausible Artificial Neural Networks

Abstract

This paper presents a simulation of a biological more plausible neural network system. The system modeled a Spiking Neural Network for self-organized architecture. Recently, Spiking Neural Networks have been much considered in an attempt to achieve a more biologically realistic neural network which was coined as the third generation Artificial Neural Networks. Spiking neurons with delays to encode the information is suggested. Thus, each output node will produce a different timing which enables competitive learning. The suggested mechanism is designed and analyzed to perform self-organizing learning and preserve the inputs topology. The simulation results show that the model is feasible to perform a self-organized unsupervised learning. The mechanism is further assessed in real-world dataset for data clustering problem.