Cellular-Neural computations. Formal model and possible applications
A formal model of fine-grained parallel computations is presented, in which the connectionist method of Artificial Neural Networks is combined with the cellular-like structure of interneuron communication. The model is based on the concepts and formalisms of Parallel Substitution Algorithm, which is considered be the most theoretically advanced generalization of Cellular Automaton. Some fields of application are discussed and computer simulation results are given.
Unable to display preview. Download preview PDF.
- 1.von Neumann J.: Theory of Self-Reproducing Automata, ed. A.W. Burks. University of Illinois Press, Urbana and London, 1966, 382p.Google Scholar
- 2.Mc-Culloch W.S., W.Pitts W.: A Logical Calculus of the Ideas Immanent in Nervous Activity. Bull.of Math. Biophysics. 5, p. 115.Google Scholar
- 3.Achasova S., Bandman O., Markova V., Piskunov S.: Parallel Substitution Algorithm. Theory and Application. World Scientific, Singapore (1995) 240 p.Google Scholar
- 4.Hopfield J.J., Tank D.W.: Computing with Neural Circuits: a Model. Science. 233 (1986) p. 625.Google Scholar
- 5.Korst J.H.M., Aarts E.H.L.: Combinatorial Optimization on Boltzmann Machine. Journ. of Parallel and Distributed Computing. 6 (1989) p. 331.Google Scholar
- 6.Chua L.O, Yang I.: Cellular Neural Networks: Theory amd Application. IEEE Transactions, CS-35, N 10 (1988) p. 1257.Google Scholar
- 7.Zhang J., Zhang I., Yan D., He A., Liu L.: Local Interconnection Neural Network and its Optical Implementation. Optics Communication. 102 (1993) p. 13.Google Scholar
- 8.Liu D., Michel A.: Sparsely Interconnected Artificial Neuron Networks for Associative Memories. Lecture Notes in Comp. Sci. 606 p. 155.Google Scholar
- 9.Rosenblatt F.: Principles of Neurodumamics. Washington, Spartan. (1959).Google Scholar