ABSTRACT
In this paper we investigate the effect of biasing the axonal connection delay values in the number of polychronous groups produced for a spiking neuron network model. We use an estimation of distribution algorithm (EDA) that learns tree models to search for optimal delay configurations. Our results indicate that the introduced approach can be used to considerably increase the number of such groups.
- R. Etxeberria and P. Larranaga. Global optimization using Bayesian networks. In A. Ochoa, M. R. Soto, and R. Santana, editors, Proceedings of the Second Symposium on Artificial Intelligence (CIMAF-99), pages 151--173, 1999.Google Scholar
- S. Kauffman. Origins of Order. Oxford University Press, 1993.Google Scholar
- M. Pelikan. Analysis of estimation of distribution algorithms and genetic algorithms on NK landscapes. In Proceedings of the Genetic and Evolutionary Computation Conference GECCO-2009, pages 1033--1040. ACM, 2008. Google ScholarDigital Library
- M. Rubinov, S. A. Knock, C. J. Stam, S. Micheloyannis, A. W. F. Harris, L. M. Williams, and M. Breakspear. Complex network measures of brain connectivity: Uses and interpretations. Neuroimage, 52(3):1059--1069, 2010.Google ScholarCross Ref
- R. Santana, C. Bielza, and P. Larranaga. Network measures for re-using problem information in EDAs. Technical Report UPM-FI/DIA/2010--3, Department of Artificial Intelligence, Faculty of Informatics, Technical University of Madrid, June 2010.Google Scholar
Index Terms
- Maximizing the number of polychronous groups in spiking networks
Recommendations
Self-organization process in large spiking neural networks leading to formation of working memory mechanism
IWANN'13: Proceedings of the 12th international conference on Artificial Neural Networks: advances in computational intelligence - Volume Part IThe subject of this work is evolutionary process in initially chaotic and homogenous spiking neural networks leading to formation of the neuron groups with partially synchronized activity (so called polychronous groups) which are not only capable of ...
Improved Izhikevich neurons for spiking neural networks
Spiking neural networks constitute a modern neural network paradigm that overlaps machine learning and computational neurosciences. Spiking neural networks use neuron models that possess a great degree of biological realism. The most realistic model of ...
Evaluating the effect of spiking network parameters on polychronization
ICANN'12: Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part ISpiking neural networks (SNNs) are considered to be more biologically realistic compared to typical rate-coded networks as they can model closely different types of neurons and their temporal dynamics. Typical spiking models use a number of fixed ...
Comments