Connection Science · 1992 · 59 citations · 21 references
ComputingComputer ScienceNeuroscienceComputational NeuroscienceMachine LearningNeurophysiologyLearning In Neural SystemsNeural Basis Of LearningNeural NetworksNeural Signal ProcessingNeural System ModelingPattern RecognitionFeedforward Neural NetworksLearning RulesMultilayer NetworksNeural Network ClassificationNeural Representation LearningRadial Basis Function Networks
A modification of the generalized delta rule is described that is capable of training multilayer networks of value units, i.e. units defined by a particular non-monotonic activation function, the Gaussian, For simple problems of pattern classification, this rule produces networks with several advantages over standard feedforward networks: they require fewer processing units and can be trained much more quickly. Though superficially similar, there are fundamental differences between the networks trained by this new learning rule and radial basis function networks. These differences suggest that value unit networks may be better suited for learning some pattern classification tasks and for answering general questions related to the organization of neurophysiological systems.
21
Learning representations by back-propagating errors
David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams · Nature · 1986 · 30.9K citations
An introduction to computing with neural nets
Richard P. Lippmann · IEEE ASSP Magazine · 1987 · 7.9K citations