Patent
1995-06-07
1997-12-23
Downs, Robert W.
G06F 1518
Patent
active
057013977
ABSTRACT:
In each neuron in a neural network of a plurality of neuron circuits either in an engaged or a free state, a pre-charge circuit, that allows loading the components of an input vector (A) only into a determined free neuron circuit during a recognition phase as a potential prototype vector (B) attached to the determined neuron circuit. The pre-charge circuit is a weight memory (251) controlled by a memory control signal (RS) and the circuit generating the memory control signal. The memory control signal identifies the determined free neuron circuit. During the recognition phase, the memory control signal is active only for the determined free neuron circuit. When the neural network is a chain of neuron circuits, the determined free neuron circuit is the first free neuron in the chain. The input vector components on an input data bus (DATA-BUS) are connected to the weight memory of all neuron circuits. The data therefrom are available in each neuron on an output data bus (RAM-BUS). The pre-charge circuit may further include an address counter (252) for addressing the weight memory and a register (253) to latch the data output on the output data bus. After the determined neuron circuit has been engaged, the contents of its weight memory cannot be modified. Pre-charging the input vector during the recognition phase makes the engagement process more efficient and significantly reduces learning time in learning the input vector.
REFERENCES:
patent: 4326259 (1982-04-01), Cooper et al.
patent: 5119469 (1992-06-01), Alkon et al.
patent: 5165010 (1992-11-01), Masuda et al.
patent: 5214743 (1993-05-01), Asai et al.
patent: 5222193 (1993-06-01), Brooks et al.
patent: 5444822 (1995-08-01), Sinohara
patent: 5479574 (1995-12-01), Glier et al.
patent: 5487133 (1996-01-01), Park et al.
patent: 5504838 (1996-04-01), Furuta et al.
patent: 5517597 (1996-05-01), Aparicio IV et al.
patent: 5517600 (1996-05-01), Shimokawa
patent: 5524175 (1996-06-01), Sato et al.
patent: 5621863 (1997-04-01), Boulet et al.
Omlin et al., Training recurrent neural network with Temporal input encodings, 1994 IEEE International conference on neural networks, pp. 1267-1272, Jul. 2, 1994.
M. Holler, et al, "A High Performance Adaptive Classifier Using Radial Basis Functions" Submitted to Government Microcircuit Applications Conference, Nov. 9-12, 1992, Las Vegas, Nevada, pp. 1-4.
Louis Didier
Paillet Guy
Steimle Andre
Downs Robert W.
International Business Machines - Corporation
Schnurmann H. Daniel
Shah Sanjiv
LandOfFree
Circuit for pre-charging a free neuron circuit does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Circuit for pre-charging a free neuron circuit, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Circuit for pre-charging a free neuron circuit will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1807013