Artificial neural network method and architecture adaptive signa

Details Artificial neural network method and architecture adaptive signa Artificial neural network method and architecture adaptive signa

1994-08-15

1995-11-14

Moore, David K.

395 21, 395 24, 395 27, G06F 1518

Patent

active

054674280

ABSTRACT:
An architecture and data processing method for a neural network that can approximate any mapping function between the input and output vectors without the use of hidden layers. The data processing is done at the sibling nodes (second row). It is based on the orthogonal expansion of the functions that map the input vector to the output vector. Because the nodes of the second row are simply data processing stations, they remain passive during training. As a result the system is basically a single-layer linear network with a filter at its entrance. Because of this it is free from the problems of local minima. The invention also includes a method that reduces the sum of the square of errors over all the output nodes to zero (0.000000) in fewer than ten cycles. This is done by initialization of the synaptic links with the coefficients of the orthogonal expansion. This feature makes it possible to design a computer chip which can perform the training process in real time. Similarly, the ability to train in real time allows the system to retrain itself and improve its performance while executing its normal testing functions. Because the second synaptic link values represent the frequency spectrum of the signal appearing on a given output node, by training the ONN with all N sibling nodes and using only some of them in testing, we can create a low pass, a high pass or a band pass filter.

REFERENCES:
patent: 4317197 (1982-02-01), Ulug
patent: 4858147 (1989-08-01), Conwell
patent: 4906940 (1990-03-01), Greene et al.
patent: 4912652 (1990-03-01), Wood
patent: 4918620 (1990-04-01), Ulug
patent: 4933872 (1990-06-01), Vandenberg et al.
patent: 4941122 (1990-07-01), Weideman
patent: 4951239 (1990-08-01), Andes et al.
patent: 4962342 (1990-10-01), Mead et al.
patent: 4965443 (1990-10-01), Yamasaki et al.
patent: 4979126 (1990-12-01), Pao et al.
patent: 5067095 (1991-11-01), Peterson et al.
patent: 5073867 (1991-12-01), Murphy et al.
patent: 5101361 (1992-03-01), Eberhardt
patent: 5103496 (1992-04-01), Andes et al.
patent: 5120996 (1992-06-01), Mead et al.
patent: 5150450 (1992-09-01), Swenson et al.
patent: 5155802 (1992-10-01), Mueller et al.
patent: 5181171 (1993-01-01), McCormack et al.
patent: 5187680 (1993-02-01), Engear
patent: 5195169 (1993-03-01), Kamiya et al.
patent: 5204938 (1993-04-01), Skapura et al.
Qian et al; "Function approximation with an Orthogonal Basis Net"; IJCNN, Jun. 1990, III-605 to III-619.
Bailey et al "Why VLSI Implementations of Associative VLCN, Require Connection multiplexing"; IEEE, 1988 112-119.
Rumelhart et al., "Learning Internal Representations by Error Propagation," Parallel Distributed Processing, vol. 1, Foundations, Rumelhart and McClelland, eds, MIT Press, Cambridge, Mass. (1986), pp. 318-362.
Thro, Ellen, "The Artificial Intelligence Dictionary", 1991, p. 148. Microtrend Books.
Le Cun et al., "Optical Character Recognition and Neural-Net Chips," International Neural Network Conference, Jul. 1990, pp. 651-655.
Omatu et al., "Neural Network Model for Alphabetical Letter Recognition," International Neural Network Conference, Jul. 1990, pp. 19-22.
Sharaf et al, "Transient stability and critical clearing time classification using neural networks"; APSCO-93, p. 365-372 vol. 1, 7-10 Dec. 1993.
Floyd et al, "Artificial neural networks for SPECT image reconstruction with optimized weighted backpropagation"; Conference record of the 1991 IEEE Nuclear Science Symposium and Medical Imaging Conference, pp. 2184-2188 vol. 3, 2-9 Nov. 1991.
Upadhyaya et al, "Development and application of neural network alogrithms for process diagnostics"; Proceedigns of the 29th IEEE Conference on Decision and Control, pp. 3277-3282 vol. 6, 5-7 Dec. 1990.

Affiliated with

Also associated with

Rating

Artificial neural network method and architecture adaptive signa does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Artificial neural network method and architecture adaptive signa, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Artificial neural network method and architecture adaptive signa will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1226965