Computer and Information Sciences: Collected Papers on Learning, Adaptation and Control in Information Systems |
Contents
INTRODUCTION | 12 |
SOME FUNDAMENTAL THEOREMS OF PERCEPTRON THEORY | 67 |
DETERMINATION AND DIRECTION OF FEATURES IN PATTERNS | 75 |
Copyright | |
1 other sections not shown
Other editions - View all
Common terms and phrases
A-units active Adaline adaptive algorithm applied artificial intelligence associator assumed automata automaton behavior billion-gate computer boundary C-system circuit cognitive concept conditional probabilities considered control system convergence corresponding covering homotopy decision function decision theory defined described determined dipsome discussed distribution elements equation equivalent example Figure filter functor given heuristic homotopy hyperplane hypersphere input intelligence intersection learning linear logic machine mapping mathematical matrix measurement space measurements mechanism memory method neuron noological normal obtained operation optimum organization output P₁ parameters particular partition pattern classes pattern recognition perceptron performance possible present probability problem procedure properties represent S₁ sample self-organizing self-organizing system semigroup sequence shown in Fig signals situation solution space statistical statistically independent stimulus strongly connected structure subset supervised learning symmetric theorem theory threshold tion units values variables vector weights zero