Analog hardware for learning neural networks

Details Analog hardware for learning neural networks Analog hardware for learning neural networks

1989-12-28

1991-10-08

MacDonald, Allen R.

Boots, shoes, and leggings

364807, G06G 712

Patent

active

050560379

ABSTRACT:
This is a recurrent or feedforward analog neural network processor having a multi-level neuron array and a synaptic matrix for storing weighted analog values of synaptic connection strengths which is characterized by temporarily changing one connection strength at a time to determine its effect on system output relative to the desired target. That connection strength is then adjusted based on the effect, whereby the processor is taught the correct response to training examples connection by connection.

REFERENCES:
patent: 3601811 (1971-08-01), Yoshino
patent: 4593367 (1986-06-01), Slack et al.
patent: 4660166 (1987-04-01), Hopfield
patent: 4737929 (1988-04-01), Denker
patent: 4773024 (1988-09-01), Faggin et al.
patent: 4796199 (1989-01-01), Hammerstrom et al.
patent: 4802103 (1989-01-01), Faggin et al.
patent: 4805225 (1989-02-01), Clark
patent: 4807168 (1989-02-01), Moopenn et al.
patent: 4809193 (1989-02-01), Jourjine
patent: 4873455 (1989-10-01), de Chambost et al.
patent: 4874963 (1989-10-01), Alspector
patent: 4901271 (1990-02-01), Graf
patent: 4912649 (1990-03-01), Wood
patent: 4918618 (1990-04-01), Tomlinson, Jr.
patent: 4933872 (1990-06-01), Vandenberg et al.
patent: 4945494 (1990-07-01), Penz et al.
patent: 4951239 (1990-08-01), Andes et al.
"A General Purpose Digital Architecture for Neural Network Simulations", M. Duranton and N. Mauduit, First IEE International Conf. on Artificial Neural Networks, Oct. 16-18, 1989.
"Pulse Arithmetic in VLSI Neural Networks", IEEE Micro, Alan F. Murray, Dec. 14, 1989.
"Neural Computing--Theory and Practice", Philip D. Wasserman, Apr. 1989.

Affiliated with

Also associated with

Rating

Analog hardware for learning neural networks does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Analog hardware for learning neural networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Analog hardware for learning neural networks will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-262291