Collective Computation With Continuous Variables
- 174 Downloads
The model on which collective computation in neural networks was originally shown to produce a content addressable memory was based on neurons with two discrete states (1) (or levels of activity) which might be thought of as “0” and “1”. That model involved an asynchronous updating of the state of each neuron, and could be closely related to aspects of magnetic Ising systems. The role of exchange in the magnetic system is played by the connections between the neurons in the biological system.
KeywordsEnergy Function Travel Salesman Problem Spin Glass Graph Link Steep Descent Path
Unable to display preview. Download preview PDF.
- 2.Perkel, D. H. and Bulloch, T. H. Neurosci. Res. Symp. Summ. 3, 405–527.Google Scholar
- 6.Denker, J. (private communication); see also Jackson, A. S. “Analog Computation” McGraw Hill, New York (1960) p. 357.Google Scholar
- 7.Hopfield, J. J. and Tank D. W., Biol. Cybernetics 52. (1985).Google Scholar