Neural network architecture for gaussian components of a mixture

Details Neural network architecture for gaussian components of a mixture Neural network architecture for gaussian components of a mixture

1995-07-07

1998-08-04

Downs, Robert W.

G06F 1518, G06E 300

Patent

active

057907587

ABSTRACT:
A neural network for classifying input vectors to an outcome class under the assumption that the classes are characterized by mixtures of component populations having a multivariate Gaussian likelihood distribution. The neural network comprises an input layer for receiving components of an input vector, two hidden layers for generating a number of outcome class component values, and an output layer. The first hidden layer includes a number of first layer nodes each connected receive input vector components and generate a first layer output value representing the absolute value of the sum of a function of the difference between each input vector component and a threshold value. The second hidden layer includes a plurality of second layer nodes, each second layer node being connected to the first layer nodes and generating an outcome class component value representing a function related to the exponential of the negative square of a function of the sum of the first layer output values times a weighting value. The output layer includes a plurality of output nodes, each associated with an outcome class, for generating a value that represents the likelihood that the input vector belongs to that outcome class.

REFERENCES:
patent: 5220618 (1993-06-01), Sirat et al.
patent: 5276771 (1994-01-01), Manukian et al.
patent: 5408585 (1995-04-01), Burel
patent: 5455892 (1995-10-01), Minot et al.
patent: 5479576 (1995-12-01), Watanabe et al.
patent: 5568591 (1996-10-01), Minot et al.
patent: 5572597 (1996-11-01), Chang et al.
Streit et al., Maximum likelihood training of probabilistic Neural Networ IEEE transactions on neural networks vol. 5, pp. 764-783, Sep. 1994.
Streit, A neural network for optimum Neyman-Pearson classification, IJCNN International joint conference on neural network, pp. 685-690, Jun. 21, 1990.
Goodman et al., A learning algorithm for multi-layer preceptrons with hard-limiting threshold units, 1994 IEEE conference on neural networks, pp. 193-197, Jul. 2, 1994.
Lippman, A critical overview of neural network pattern classifiers, 1991 IEEE workshop, pp. 266-275, Oct. 1, 1991.
Musavi et al., Improving the performance of probabilistic neural networks, IJCNN International joint conference on Neural networks, pp. 595-600, Jun. 11, 1992.
Farrell et al., Neural tree network/vector quantization probability estimators for speaker recognition, Neural network for signal processing IV Proceedings of 1994 IEEE workshop, pp. 279-288, Sep. 8, 1994.
Tarassenko et al., Supervised and unsupervised learning in radial basis function classifiers, IEE proceedings, pp. 210-216, Aug. 1994.
McMicheal, Bayesian growing and pruning strategies for MAP-optimal estimation of Gaussian mixture models, Fourth International conference on artificial neural networks, pp. 364-368, Jun. 28, 1995.
Kosonocky et al., A continious density neural tree network word spotting system, 1995 International conference on Acoustics, Speech and signal processing, pp. 305-308, May 12, 1995.

Affiliated with

Also associated with

Rating

Neural network architecture for gaussian components of a mixture 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 architecture for gaussian components of a mixture, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network architecture for gaussian components of a mixture will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1187639