Acceleration of learning in hybrid neural networks: A novel approach for the design of brain chaosmakers

B.L. Bardakjian1, A. Chiu1
1Institute of Biomaterials and Biomedical Engineering, University of Toronto, Toronto, Canada

Tóm tắt

Epileptic seizures correspond to episodes of increased rhythmicity of the normally chaotic activity in biological neural networks. We propose to use hybrid neural networks where artificial neural networks are used to control the biological neural networks by learning their different states. The learning is dramatically accelerated when using a conjugate gradient method in conjunction with the Fletcher-Reeves method of optimization.

Từ khóa

#Acceleration #Intelligent networks #Biological neural networks #Chaos #Artificial neural networks #Character generation #Epilepsy #Optimization methods #Voltage #Biomedical engineering

Tài liệu tham khảo

10.1038/363411a0 fletcher, 1990, Practical Methods of Optimization 10.1038/370615a0 10.1142/S0218127492000653