Application of the Levenberg-Marquardt method to the training of spiking neural networks

Silva, S. M.; Ruano, Antonio

http://hdl.handle.net/10400.1/2243

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
017166471.pdf		128.76 KB	Adobe PDF	Download

Send Feedback

Authors

Silva, S. M.

Ruano, Antonio

Abstract(s)

One of the basic aspects of some neural networks is their attempt to approximate as much as possible their biological counterparts. The goal is to achieve a simple and robust network, easy to comprehend and capable of simulating the human brain at a computational level. This paper presents improvements to the Spikepro algoritm, by introduting a new encoding scheme, and illustrates the application of the Levenberg Marquardt algorithm to this third generation of neural network.

URI

http://hdl.handle.net/10400.1/2243

Citation

Silva, S. M.; Ruano, A. E. Application of the Levenberg-Marquardt method to the training of spiking neural networks, Trabalho apresentado em The 2006 IEEE International Joint Conference on Neural Network Proceedings, In Proceedings of the 2006 IEEE International Joint Conference on Neural Network Proceedings, Vancouver, BC, Canada, 2006.