Towards a Biological More Plausible Artificial Neural Networks
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.
KeywordsSpiking Neural Network(SNN) Self-organized
Unable to display preview. Download preview PDF.
- 1.Gerstner, W., Kistler, W.: Spiking Neuron Models. Cambridge Univ. Press (2002)Google Scholar
- 3.Maass, W.: Computing with Spiking Neurons. In: Maass, W., Bishop, C.M. (eds.) Pulsed Neural Network, pp. 55–85. MIT Press (1998)Google Scholar
- 4.Panchev, C., Wermter, S.: Hebbian Spike-Timing Dependent Self-Organization in Pulsed Neural Networks. In: Proceedings of World Congress on Neuroinformatics (2001)Google Scholar
- 6.Sala, D.M., Cios, K.J.: Self-organization in networks of spiking neurons. Australian Journal of Intelligent Information Processing Systems 5(3), 161–170 (1998)Google Scholar
- 7.UCI repository of machine learning databases, http://archive.ics.uci.edu/ml