Discriminant neural networks

Details Discriminant neural networks Discriminant neural networks

1994-07-01

1999-07-20

Downs, Robert W.

Data processing: artificial intelligence

Neural network

Learning method

706 16, G06F 1518

Patent

active

059268042

ABSTRACT:
A discriminant neural network and a method of training the network are disclosed. The network includes a set of hidden nodes having associated weights, and the number of hidden nodes is minimized by the training method of the invention. The training method includes the steps of 1) loading a training data set and assigning it to a residual data set, 2) computing a vector associated with a first hidden node using the residual data set, 3) projecting training data onto a hyperplane associated with said first hidden node, 4) determining the number and locations of hard-limiter thresholds associated with the first node, and 5) repeating the above for successive hidden nodes after removing satisfied subsets from the training data until all partitioned regions of the input data space are satisfied.

REFERENCES:
patent: 5359700 (1994-10-01), Seligson
patent: 5469530 (1995-11-01), Makrak-Ebeid
patent: 5490236 (1996-02-01), Niki
Baum et al., Constructing hidden units using examples and queries, Advances in neural processing systems 3, 1991, pp. 904-910.
Baum, Neural net algorithms that learn in polynomial time from examples and queries, IEEE transactions on neural networks, pp. 5-19, Jan. 1991.
Strobach, A neural network with boolean output layer, International conference on Acoustics, Speech and Signal processing, pp. 2081-2084, Apr. 6, 1990.
Farrell et al., Speaker identification using neural tree networks, IEEE International conference on acoustics, speerh and signal processing, pp. I/165-I/168, Apr. 22, 1994.
Koutsougeras et al., Training of a neural network for pattern classification based on an entropy measure, IEEE international conference on neural networks, pp. 247-254, Jul. 27, 1988.
Monrocq, A probabilistic approach which provides a modular and adaptive neural network architecture for discrimination, Third international conference on artificial neural network, pp. 252-256, May 27, 1993.
Moore et al., Characterizing the error function of a neural network, Proceedings. The second symposium on the frontiers of massively parallel computation, pp. 49-57, Oct. 12, 1988.
Williams, Improved generalization and network pruning using adaptive laplace regularization, Third international conference on artificial neural networks, pp. 76-80, May 27, 1993.
Diaz et al., SLHMM: a continious speech recognition system based on Alphanet-HMM, IEEE international conference on acoustics, speech and signal processing, pp. I/213-16, Apr. 22, 1994.

Affiliated with

Also associated with

Rating

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

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1331655