Training neural networks

Details Training neural networks Training neural networks

1988-12-14

1990-04-03

Lastova, John R.

Boots, shoes, and leggings

364200, 3642213, 3642749, 364900, 3649162, 3649724, G06E 1518

Patent

active

049146033

ABSTRACT:
A method of training an artificial neural network uses a computer configured as a plurality of interconnected neural units arranged in a layered network including an input layer having a network input, and an output layer having a network output. A neural unit has a first subunit and a second subunit. The first subunit having one or more first inputs, and a corresponding first set of variables for operating upon the first inputs to provide a first output. The first set of variables can change in response to feedback representing differences between desired network outputs for selected network inputs and actual network outputs. The second subunit has a plurality of second inputs, and a corresponding second set of variables for operating upon said second inputs to provide a second output. The second set of variables can change in response to differences between desired network outputs for selected network inputs and actual network outputs. The computer provides an activating variable representing the difference between current second output and previous second outputs. A series of examples of data is provided as network input to said network. The activating variable is added to the feedback to accelerate the change of said first set of variables. The actual resulting network outputs are compared to desired outputs corresponding to the examples. The examples are iterated until the network outputs converge to a solution.

REFERENCES:
patent: 3533072 (1970-10-01), Clapper
patent: 3950733 (1976-04-01), Cooper
patent: 4254474 (1981-03-01), Cooper
patent: 4326259 (1982-04-01), Cooper
patent: 4660166 (1987-04-01), Hopfield
patent: 4807168 (1989-02-01), Moopenn et al.
Neural Networks, Part 2, Wasserman et al., IEEE Expert, Spring 1988, pp. 10-15.
"An Intro. to Computing with Neural Nets", Lippmann, IEEE ASSP Magazine, 4/87, pp. 4-22.
"Experiments on Learning by Back Propagation", Plaut et al., Carnegie-Mellon Univ., Dept. Computer Science, pp. 1-47, 6-86.
"Back-Propagation Networks for Event-Driven Temporal Sequence Processing", Shimohara et al., IEEE International Conference on Neural Networks, 7-88, pp. 665-672.
"Increased Effectiveness of Learning by Local Neural Feedback", Sobajic et al., Abstract of First INNS Meeting, vol. 1, Supp. 1, 1988, p. 222.
"Accelerating the Convergence of the Back Propagation Method", Vogl et al., Bio. Cybern. 59, 257-263, Spring 1988.

Affiliated with

Also associated with

Rating

Training 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 Training neural networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Training neural networks will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1362625