Title :
Design principles for an intelligent machine
fDate :
9/1/1962 12:00:00 AM
Abstract :
This paper discusses the role of prediction as the key process underlying the function of an intelligent machine. A model of a "neuron" is presented which exhibits properties of memory and learning. The formalism of the calculus of probability allows us to interpret the behavior of a neuron in such a way as to justify how a network of such elements can be organized so that it can learn to predict.
Keywords :
Prediction methods; Brain modeling; Calculus; Circuit simulation; Computational modeling; Computer simulation; Discrete event simulation; Intelligent systems; Learning systems; Machine intelligence; Neurons; Predictive models;
Journal_Title :
Information Theory, IRE Transactions on
DOI :
10.1109/TIT.1962.1057751
