Neural device and method of constructing the device

Details Neural device and method of constructing the device Neural device and method of constructing the device

1995-06-05

1997-07-15

Hafiz, Tariq R.

395 21, 395 20, G06E 100, G06E 300, G06F 1518

Patent

active

056490674

ABSTRACT:
On the basis of a device without hidden neurons, arbitrary samples are taken from a set of learning samples so as to be presented as objects to be classified. Each time if the response is not correct, a hidden neuron (H.sub.i) is introduced with a connection to the output neuron (O.sub.j) of the class of the sample, whereas if the response is correct, no neuron whatsoever is added. During this introduction phase for hidden neurons, the neurons are subdivided into groups by searching for each of the introduced neurons whether it falls within an existing group, in which case it is incorporated therein; otherwise a new group is created around this neuron. The association with a group is defined as a function of the distance from the "creator" neuron. This device could be applied in character recognition systems as one example.

REFERENCES:
patent: 4933872 (1990-06-01), Vandenberg et al.
patent: 4975961 (1990-12-01), Sakoe
patent: 5033006 (1991-07-01), Ishizuka et al.
patent: 5052043 (1991-09-01), Gaborski
patent: 5067095 (1991-11-01), Peterson et al.
patent: 5129039 (1992-07-01), Hiraiwa
patent: 5134396 (1992-07-01), Sirat et al.
patent: 5146541 (1992-09-01), Speidel
patent: 5175796 (1992-12-01), Refreigier et al.
patent: 5182794 (1993-01-01), Gasperi et al.
patent: 5228113 (1993-07-01), Shelton
patent: 5239594 (1993-08-01), Yoda
patent: 5245697 (1993-09-01), Suzuoka
patent: 5259039 (1993-11-01), Kamatsu
patent: 5276771 (1994-01-01), Manukian et al.
patent: 5280564 (1994-01-01), Shiomi et al.
"The Piecewise Linear Neural Network: Training and Recognition", by Y.H. Kong et al, IJCNN International Joint Conference on Neural Networks, Jun. 17-21, 1990, pp. II-245 to III-250.
"Unsupervised learning for Neural Trees", by L. Fang et al, 1991 IEEE International Joint Conference on Neural Networks, Nov. 18-21, 1991, pp. 2709-2715.
Stokbro et al., "Exploiting Neurons with Localized Receptive Fields to Learn Chaos", Complext Systems, No. 4, (1990), 603-622.
Platt, "Learning by Combining Memorization and Gradient Descent", pp. 714-720, from Advances, a Neural Inforamtion Processing, 1991, vol. 1, Morgan Kaufman Ed (Palo Alto).
Omohundro, "Bumptree for Efficient Function, Constraint, and Classification Learning", pp. 693-699, from Advances in Neural Inforamtion Processing, 1991, vol. 3, Morgan Kaufman Ed. (Palto Alto).
Reilly et al., "A Neural Model for Category Learning", Biological Cybernetics, vol. 45, pp. 35-41, (1982).

Affiliated with

Also associated with

Rating

Neural device and method of constructing the device 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 device and method of constructing the device, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural device and method of constructing the device will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1498103