Artificial Neural Networks: Approximation and Learning Theory

摘要: From the Publisher: The recent re-emergence of network-based approaches to artificial intelligence has been accomplished by a virtual explosion research. This research spans range disciplines - cognitive science, computer biology, neuroscience, electrical engineering, psychology, econometrics, philosophy, etc. which is, perhaps, wider than any other contemporary endeavor. Of all contributing relatively universal language mathematics provides some most powerful tools for answering fundamental questions about capabilities and limitations these 'artificial neural networks'. In this collection, Halbert White his colleagues present rigorous mathematical analysis approximation learning leading class single hidden layer feedforward networks. Drawing together work previously scattered in space time, book gives unified view network not available location, forges links between modern statistics.