论文信息 - Design principles for an intelligent machine

Design principles for an intelligent machine

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.

M. E. Maron

[1] Marvin Minsky,et al. Steps toward Artificial Intelligence , 1995, Proceedings of the IRE.

[2] R. L. Beurle. Storage and manipulation of information in the brain , 1959 .

[3] J. K. Hawkins. Self-Organizing Systems-A Review and Commentary , 1961, Proceedings of the IRE.

[4] N. Wiener,et al. Behavior, Purpose and Teleology , 1943, Philosophy of Science.

[5] H. Reichenbach. Experience and Prediction. An Analysis of the Foundations and the Structure of Knowledge , 1938 .

[6] D. Mackay,et al. Towards an information-flow model of human behaviour. , 1956, British journal of psychology.