Patent
1994-09-15
1997-09-23
Hafiz, Tariq R.
395 21, 395 27, G06E 100, G06E 300, G06F 1518
Patent
active
056713363
ABSTRACT:
An apparatus based on an n-variable unlimited recurrent adjustable network (URAN.sub.n) comprises: two layers, each layer having the same number (n) of neuron elements; linear neuron elements x.sub.i constituting a first layer; nonlinear artificial neuron elements y.sub.j having respective temperature-dependent parameters Tj and constituting a second layer. Each linear and nonlinear neuron element of the first and second layers is connected using a feedforward connection part, a recurrent connection part, and an auto connection part. A nonlinear oscillation apparatus having the recurrent neural network is generally operated in accordance with the equation (1) described below: ##EQU1##
REFERENCES:
patent: 5371834 (1994-12-01), Tawel
patent: 5408424 (1995-04-01), Lo
patent: 5412754 (1995-05-01), Le Cun et al.
Yoshida et al, "On the architecture of a recurrent neural network as a chaos 1/f generator"; Proceedings of hte 1995 IEEE Internatonal Conference on Fuzzy Systems. The International joint conference of the fourth IEEE international conference on fuzzy sy Mar. 1995.
Hakim et al, "Volterra characterization of neural networks"; Conference record of the twenty-fifth Asilomar conference on signals, systems and computers, pp. 1128-1132 vol. 2, 4-6 Nov. 1991. Nov. 1991.
Youlal et al, "Fast diagonal recurrent neural networks for identification and control of non-linear systems"; International conference on control 94', pp. 104-109 vol. 1, 21-24 Mar. 1994.
deFigueiredo, "A neural network model for nonlinear predictive coding in Fock space"; 1993 IEEE International symposium on circuits and systems, pp. 2164-2167 vol. 4, 3-6 May 93.
"An Introduction to Neurocomputing", edited by Kaoru Nakano, p. 143, published by Corona Publishing, Apr. 5, 1990.
"The New IEEE Standard Dictionary of Electrical and Electronics Terms", 5th edition, p. 716, 1992.
"On the Recurrent Neural Networks", Kenu-ichi Funahashi, Toyohashi University of Technology, The Institute of Electronics, Information and Communication Engineers, 1992.
"Chaos In Neural System", Chapter 7, 1993, pp. 245-283.
Kishi Norimasa
Yoshida Kazumi
Hafiz Tariq R.
Nissan Motor Co,. Ltd.
LandOfFree
Apparatus based on n-variable unlimited recurrent adjustable net does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Apparatus based on n-variable unlimited recurrent adjustable net, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Apparatus based on n-variable unlimited recurrent adjustable net will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1941499