Data processing: artificial intelligence – Neural network – Learning method
Patent
1997-07-07
1998-09-01
MacDonald, Allen R.
Data processing: artificial intelligence
Neural network
Learning method
706 20, G06F 1518
Patent
active
058025073
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. Application: character recognition systems.
REFERENCES:
patent: 4933872 (1990-06-01), Vandenberg et al.
patent: 4941122 (1990-07-01), Wideman
patent: 4975961 (1990-12-01), Sakoe
patent: 5033006 (1991-07-01), Ishizuki
patent: 5052043 (1991-09-01), Gaborski
patent: 5060278 (1991-10-01), Fukumizu
patent: 5067095 (1991-11-01), Peterson et al.
patent: 5067164 (1991-11-01), Denker
patent: 5129039 (1992-07-01), Hiraiwa
patent: 5134396 (1992-07-01), Sirat et al.
patent: 5146541 (1992-09-01), Speidel
patent: 5155801 (1992-10-01), Lincoln
patent: 5175796 (1992-12-01), Refregier et al.
patent: 5182794 (1993-01-01), Gasperi et al.
patent: 5228113 (1993-07-01), Shelton
patent: 5239594 (1993-08-01), Yoda
patent: 5239619 (1993-08-01), Takatori
patent: 5245697 (1993-09-01), Suzuoka
patent: 5257342 (1993-10-01), Takatori
patent: 5259039 (1993-11-01), Akamatsu
patent: 5259065 (1993-11-01), Takatori
patent: 5276771 (1994-01-01), Manukian et al.
patent: 5280564 (1994-01-01), Shiomi et al.
patent: 5317675 (1994-05-01), Ikehara
patent: 5355437 (1994-10-01), Takatori
patent: 5361328 (1994-11-01), Takatori
patent: 5371809 (1994-12-01), Desieno
patent: 5371834 (1994-12-01), Tawel
patent: 5438629 (1995-08-01), Moed
patent: 5479575 (1995-12-01), Yoda
Reilly et al., "A Neural Model For Category Learning", Biological Cybernetics, vol. 45, pp. 35-41, (1982).
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 Information 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 Information Processing, 1991, vol. 3, Mrogan Kaufman Ed. (Palo Alto).
"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. III-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.
Gentric Philippe
Minot Joel
MacDonald Allen R.
Smith Jeffrey S.
U.S. Philips Corporation
LandOfFree
Method for constructing a neural device for classification of ob does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method for constructing a neural device for classification of ob, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method for constructing a neural device for classification of ob will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-284060