A discussion of the role of prediction as the key process underlying the function of an intelligent machine. A model of a "neuron" is presented that exhibits properties of memory and learning. The formalism of the calculus of probability permits the behavior of a neuron to be interpreted in such a way as to justify the organization of a network of such elements so that it can learn to predict.
This report is part of the RAND Corporation research memorandum series. The Research Memorandum was a product of the RAND Corporation from 1948 to 1973 that represented working papers meant to report current results of RAND research to appropriate audiences.
The RAND Corporation is a nonprofit institution that helps improve policy and decisionmaking through research and analysis. RAND's publications do not necessarily reflect the opinions of its research clients and sponsors.