On redundancy in neural architecture: Dynamics of a simple module-based neural network and initial-state independence

Neural Networks

Volumn 12, Issue 7-8, 1999, Pages 1075-1085

  Tsutsumi, K ^a  

^a RYUKOKU UNIVERSITY   (Japan)

Author keywords

Cross coupled Hopfield nets; Dynamics; Hopfield network; Initial state; Minimum; Module; Neural network; Redundancy

Indexed keywords

ARTIFICIAL INTELLIGENCE; COMPUTER SIMULATION; FEEDBACK; MATHEMATICAL MODELS; REDUNDANCY;

CROSS COUPLED HOPFIELD NETS; HOPFIELD NETWORK; INITIAL STATE; MODULE;

NEURAL NETWORKS;

ARCHITECTURE; ARTICLE; COMPUTER ANALYSIS; DYNAMICS; HUMAN; LEARNING; NERVE CELL NETWORK; PRIORITY JOURNAL; SIMULATION;

EID: 0033213756     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(99)00051-9     Document Type: Article

References (17)

1. Carpenter G.A., Cohen M.A., Grossberg S., Kohonen T., Oja E., Palm G., Hopfield J.J., Tank D.W. Technical comments: computing with neural networks. Science. 235:1987;1226-1229.
2. Hinton G.E., Sejnowski T.J. Learning and relearning in Boltzmann machines. Rumelhart D.E., McClelland J.L., PDP Research Group. Parallel distributed processing. 1:1986;282-317 MIT Press, Cambridge, MA.
3. Hopfield J.J. Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Science, USA. 79:1982;2554-2558.
4. Hopfield J.J. Neurons with graded response have collective computational properties like those of two-state neurons. Proceedings of the National Academy of Science, USA. 81:1984;3088-3092.
5. Hopfield J.J., Tank D.W. "Neural" computation of decisions in optimization problems. Biological Cybernetics. 52:1985;141-152.
6. Kinzel W. Learning and pattern recognition in spin glass models. Zeitshrift für Physik B. 60:1985;205-213.
7. Kirkpatrick S. Optimization by simulated annealing. Science. 220:1983;671-680.
8. Kita H., Odani H., Nishikawa Y. Solving a placement problem by means of an analog neural network. IEEE Transactions on Industrial Electronics. 39:1992;543-551.
9. Kosko B. Bidirectional associative memories. IEEE Transactions on Systems, Man, Cybernetics. 18:1988;49-60.
10. Ozawa S., Tsutsumi K. A multi-module neural network model and the estimate of its nature as associative memory. The transactions of the institute of electronics, information and communication engineers (in Japanese). J-77-DII(6):1995;1135-1145. The English version of this paper is in Systems and Computers in Japan, 26 (1995) 99-110.
11. Ozawa S., Tsutsumi K., Baba N. An artificial modular neural network and its basic dynamical characteristics. Biological Cybernetics. 78:1998;19-36.
12. Rumelhart D.E., Hinton G.E., Williams R.J. Learning representations by back-propagating errors. Nature. 323:1986;533-536.
13. Tank D.W., Hopfield J.J. Simple "neural" optimization networks: an A/D converter, signal decision circuit, and a linear programming circuit. IEEE Transactions on Circuit and Systems. 33:1986;533-541.
14. Tsutsumi K. A multi-layered neural network composed of back-prop. and Hopfield nets and internal space representation. Proceedings of International Joint Conference on Neural Networks, Washington, DC. 2:1989;365-371.
15. Tsutsumi K. Cross-coupled Hopfield nets via generalized-delta-rule-based internetworks. Proceedings of International Joint Conference on Neural Networks, San Diego. 2:1990;259-265.
16. Tsutsumi K. Higher degree error backpropagation in cross-coupled Hopfield nets. Proceedings of International Joint Conference on Neural Networks, Seattle. 2:1991;349-355.
17. Wilson G.V., Pawley G.S. On the stability of the travelling salesman problem algorithm of Hopfield and Tank. Biological Cybernetics. 58:1988;63-70.