Information-Theoretic Aspects of Neural Networks
Perambur S. Neelakanta, P. S. NeelankantaISBN: 0849331986;
Information theoretics vis-a-vis neural networks generally embodies parametric entities and conceptual bases pertinent to memory considerations and information storage, information-theoretic based cost-functions, and neurocybernetics and self-organization. Existing studies only sparsely cover the entropy and/or cybernetic aspects of neural information.Information-Theoretic Aspects of Neural Networks cohesively explores this burgeoning discipline, covering topics such as:oShannon information and information dynamicsoneural complexity as an information processing systemomemory and information storage in the interconnected neural weboextremum (maximum and minimum) information entropyoneural network trainingonon-conventional, statistical distance-measures for neural network optimizationsosymmetric and asymmetric characteristics of information-theoretic error-metricsoalgorithmic complexity based representation of neural information-theoretic parametersogenetic algorithms versus neural...
- OZON.ru 15209