Neural network with learning function based on simulated anneali

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

395 24, G06F 100

Patent

active

054598176

ABSTRACT:
A neural network with a learning function which does not require the backward propagation of the signals for the learning, which is applicable for a case involving the feedback of the synapses or the loop formed by the synapses, and which enables the construction of a large scale neural network by using compact and inexpensive circuit elements. An evaluation value is calculated according to a difference between each output signal of the network and a corresponding teacher signal; a manner of updating the synapse weight factor of each synapse is determined according to an evaluation value change between a present value and a previous value of evaluation value on a basis of the simulated annealing; a randomly changing update control signal is generated according to a random number; and a synapse weight factor of each synapse is updated according to the generated update control signal and the determined manner of updating on a basis of the Monte-Carlo method.

REFERENCES:
patent: 3601811 (1971-08-01), Yoshino
patent: 4874963 (1989-10-01), Alspector
patent: 4933871 (1990-06-01), DeSieno
patent: 5134685 (1992-07-01), Rosenbluth
patent: 5148514 (1992-09-01), Arima et al.
patent: 5153923 (1992-10-01), Matsuba et al.
patent: 5195169 (1993-03-01), Kamiya et al.
patent: 5214746 (1993-05-01), Fogel et al.
patent: 5220496 (1993-06-01), Tanaka et al.
patent: 5220641 (1993-06-01), Shima et al.
patent: 5247583 (1993-09-01), Kato et al.
patent: 5253327 (1993-10-01), Yoshihara
patent: 5303328 (1994-04-01), Masui et al.
Matsuba, "Optimal Simulated Annealing Method and Its Application to Combinatorial Problems", Int'l Joint Conf on Neural Networks, Jun. 18-22, 1989, vol. 1 pp. 541-546.
Blake et al., "Visual Reconstruction," pp. 126-127 (1987).
Wong et al., "Simulated Annealing for VLSI Design," pp. 1-7 (1988).

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Neural network with learning function based on simulated anneali 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 with learning function based on simulated anneali, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network with learning function based on simulated anneali will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-604428

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.