Neural system of classification and classification method using

Details Neural system of classification and classification method using Neural system of classification and classification method using

1991-04-12

1992-12-29

Fleming, Michael R.

395 22, G06F 1518, G06K 962

Patent

active

051757966

ABSTRACT:
The disclosure concerns neural networks designed specially for the classification of objects represented by vectors X. If the vectors X include several parameters and if the objects have to be classified in a large number N of classes, the end result is a very large number of interconnections which become difficult to set up physically, are slow in their operation and require lengthy learning phases. The disclosed neural classification system has the particular feature of being constituted on the basis of P neural networks each individually carrying out the classification of objects in only two classes or, at any rate, in a small number of classes only. These networks give probabilities P.sub.i,j of membership in a class C.sub.i among two classes C.sub.i and C.sub.j. The outputs of these networks are connected to a signal processing module which, through simple functions (implementing linear combinations of the outputs and non-linear standardization functions) establishes, on N outputs, results P.sub.i (X) of classification among the N classes. The learning is done on classifications by pairs of classes, but the post-learning recognition gives classifications among N classes.

REFERENCES:
patent: 4941122 (1990-07-01), Weideman
patent: 5060278 (1991-10-01), Fukumizu
Kunihiko Fukushima et al., "Neocognitron: A Neural Network Model for a Mechanism of Visual Pattern Recognition," IEEE Transactions on Systems, Man and Cybernetics, vol SMC-13, No. 5, Sep./Oct. 1983, pp. 826-834.
Proceedings VLSI & Computer Peripherals, Compeuro'89, Hamburg, May 1989, pp. 3/170-172, IEEE, New York, US; N. K. Hasan, et al.: "Orientation Measurement of piece parts using single-layer networks".
IJCNN International Joint Conference On Neural Networks, Washington Jun. 1989; pp. I/251-258, T. Matsuoka, et al.: "Syllable recognition using integrated neural networks."

Affiliated with

Also associated with

Rating

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

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1893267