Information-Theoretic Aspects of Neural Networks

Information-Theoretic Aspects of Neural Networks is an exceptional resource for engineers and computer scientists working in the field of artificial neural networks as well as biologists applying the concepts of communication theory and protocols to the functioning of the brain. It presents focused insight as well as new perspectives on information-processing as it relates to real and artificial networks. Filled with tables and figures, it provides alternative strategies for designing and understanding complex neural networks, introduces new cost-functions, and explores new avenues in the field. The author also includes exhaustive references, some presented here for the first time.