Patent
1994-03-10
1996-12-03
Hafiz, Tariq R.
395 21, 395 24, G06E 100, G06E 300
Patent
active
055816606
ABSTRACT:
A neural network layer (1) is made up of nodes or neurons which each comprise a pair of physically separate and optically coupled sub-units (X.sub.1, Y.sub.1). One sub-unit broadcasts excitatory and receives inhibitory signals, whereas the other sub-unit broadcasts inhibitory and receives the excitatory signals. An electrical feedback connection (20) is provided between corresponding sub-units for determination of net node activation. Diffractive or holographic optical elements (2) are used for optical coupling.
REFERENCES:
patent: 4893255 (1990-01-01), Tomlinson, Jr.
patent: 5004309 (1991-04-01), Caulfield et al.
patent: 5033103 (1991-07-01), Sillart
patent: 5109425 (1992-04-01), Lawton
patent: 5121231 (1992-06-01), Jenkins et al.
patent: 5129041 (1992-07-01), Pernick et al.
patent: 5151969 (1992-09-01), Petsce
patent: 5206541 (1993-04-01), Boahen et al.
patent: 5235440 (1993-08-01), Clark et al.
Kam et al, "Design of two architectures of asynchronous binary nerual networks using linear programming"; Proceedings of the 29th IEEE Conference on Decision and Control, pp. 2766-2767 vol. 5, 5-7 Dec. 1990.
Bhatia et al, "Single layer edge detector with competitive unsupervised learning"; 1991 IEEE International Joint Conference on Neural Networks, pp. 634-639 vol. 1, 18-21 Nov. 1991.
Sheu et al, "An analog nerural network processor for self-organizing mapping"; 1992 IEEE International Solid-State Circuits Conference, pp. 136-137, 19-21 Feb. 1992.
Marshal, "Development of perceptual context-sensitivity in unsupervised neural networks: parsing, grouping, and segmentation"; IJCNN, pp. 315-320 vol. 3, 7-11 Jun. 1992.
Cheng et al, "Distribution of winners in local lateral inhibition"; IJCNN, pp. 456-461 vol. 3, 7-11 Jun. 1992.
Rybak et al, "Neural network modeling in studying neuron mechanisms of visual perception"; RNNS/IEEE symposium on neuroinformatics and neurocomputers, pp. 323-333 vol. 1, 7-10 Oct. 1992.
Bachmann et al, "Classification of simulated radar imagery using lateral inhibition neural networks"; Neural networks for signal processing II. Proceeding os the IEEE-SP workshop, pp. 279-288, 31 Aug.-2 Sep. 1992.
Petrisor et al, "Volume holographic interconnection and copying architectures based on incoherent/coherent source array"; Fourth International Conference on Holographic systems, components and applications, pp. 21-26, 13-15 Sep. 1993.
Kawakami et al, "Bidirectional optical learnable neural networks for OEIC"; 1991 IEEE International Joint Conference on Neural Networks (IJCNN), pp. 1711-1716 vol. 2, 18-21 Nov. 1991.
Optics Letters, vol. 16, No. 13, Jul. 1, 1991, Optical Society of America by Wataru Kawakami et al.: Lateral inhibitory action in an optical neural network using an internal-light-coupled optical device array.
Japanese Journal of Applied Physics, vol. 32, No. 18, Jan. 1993, Tokyo, Japan, pp. 442-446, Ishiwara: Proposal of Adaptive-Learning Neuron Circuits with Ferroelectric Analog-Memory Weights.
Research Disclosure, No. 32954, Sep. 1991, Emsworth, GB, p. 672, Disclosed Anonymously: Optical Coupling of Neighboring Neurons in Neural Networks.
Optical Engineering, vol. 29, No. 9, Sep. 1990, Bellingham, US, pp. 1107-1113, Lu et al.: Self-organizing optical neural network for unsupervised learning.
Optics Letters, vol. 14, No. 18, 15 Sep. 1989, Optical Society of America by Wataru Kawakami et al.: Demonstration of an optical inhibitory neural network.
SPIE Proceedings on Photonics for Computers, Neural Networks, and Memories, vol. 1773, Jul. 1992, San Diego, US, pp. 36-43, Chao et al.: Optical Implementation of a Shift-Invariant Neocognitron.
Hafiz Tariq R.
Hitachi , Ltd.
LandOfFree
Neural network structure having lateral interconnections does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Neural network structure having lateral interconnections, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network structure having lateral interconnections will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-792806