Learning Algorithms of Three Layered Neural Networks for Sequence Classification

抄録

Domains of classifying positive and negative patterns are derived by imposing some heteroassociative output conditions on the network. Using the shape of the domain, a functional to be minimized is introduced to determine connection weights and threshold values of the network. Minimization techniques of the functional, which give learning algorithms of the network, are also discussed. In the last, remarks on numerical experiments are described.