Designing Linear Threshold Based Neural Network Pattern Classifiers

The three problems that concern us are identifying a natural domain of pattern classification applications of feed forward neural networks, select(cid:173) ing an appropriate feedforward network architecture, and assessing the tradeoff between network complexity, training set size, and statistical reli(cid:173) ability as measured by the probability of incorrect classification. We close with some suggestions, for improving the bounds that come from Vapnik(cid:173) Chervonenkis theory, that can narrow, but not close, the chasm between theory and practice. The goal is to provide rapid, reliable classification of new inputs from a (1) pattern source. Neural networks are appropriate as pattern classifiers when the pattern sources are ones of which we have little understanding, beyond perhaps a nonparametric statistical model, but we have been provided with classified samples of features drawn from each of the pattern categories. Neural networks should be able to provide rapid and reliable computation of complex decision functions.