Adaptive Multilayer Artificial Neural Networks and Applications

摘要

Artificial Neural Networks are viewed here as parallel computational models, with varying degress of complexity, comprised of dennsely interconnected adaptive processing units. An important feature of these networks is their adaptive nature, where "Learning by Example" replaces traditional " Programming " in solving problems.rnThis paper deals with a brief introductory learning to multilayer artificial neural networks. It uses error back propagation (or back prop) learning rule which is the most frequently used learning rules in many applications of artificial neural networks. In this paper several significant applications of back prop trained multilayer nets are described. These applications include conversion of English Text to Speech , Mapping of hand gestures to speech, recognition of hand written Zip codes, continuous vehicle navigation , medical diagnosis and image compression.