Neural network for classification of patterns with improved meth

Details Neural network for classification of patterns with improved meth Neural network for classification of patterns with improved meth

1995-06-07

1998-03-17

Downs, Robert W.

395 22, 395 24, G06F 1518

Patent

active

057296626

ABSTRACT:
A type of neural network called a self-organizing map (SOM) is useful in pattern classification. The ability of the SOM to map the density of the input distribution is improved with two techniques. In the first technique, the SOM is improved by monitoring the frequency for which each node is the winning node, and splitting frequently winning nodes into two nodes, while eliminating infrequently winning nodes. Topological order is preserved by inserting a link between the preceding and following nodes so that such preceding and following nodes are now adjacent in the output index space. In the second technique, the SOM is trained by applying a weight correction to each node based on the frequencies of that node and its neighbors. If any of the adjacent nodes have a frequency greater than the frequency of the present node, then the weight vector of the present node is adjusted towards the highest-frequency neighboring node. The topological order of the nodes is preserved because the weight vector is moved along a line of connection from the present node to the highest-frequency adjacent node. This second technique is suitable for mapping to an index space of any dimension, while the first technique is practical only for a one-dimensional output space.

REFERENCES:
patent: 5371809 (1994-12-01), Desieno
patent: 5479575 (1995-12-01), Yoda
T. Kohonen, "The Self Organizing Map," Proc. of the IEEE, vol. 78, No. 9, Sep. 1990, pp. 1464-1480.
B. Fritzke, "Growing Cell Structures-A Self Organizing Network for Unsupervised Learning", Neural Networks, vol. 7, No. 9, pp. 1441-1460, 23 Mar. 1994.
H Bauer and K. Pawelzik, "Quantifying the Neighborhood Preservation of Self Organizing Maps", IEEE Transactions on Neural Nertworks, vol. 3, No. 4, Jul. 1992.
S. Haykin, "Neural Networks, A Comprehensive Foundation", IEEE Press and Macmillan College Publishing Company, New York, NY, 1994, pp. 408-422, 439, 442.
H. Yin, et al., "Inverse-Step Competitive Learning," IEEE Int'l. Joint Conf. on Neural Networks, pp. 839-844., Nov. 1991.
C. Hsu and H. Wu, "An Improved Algorithm for Kohonen's Self-organizing Feature Maps," 1992 IEEE Int'l. Symposium on Circuits and Systems, pp. 328-331., May 1992.
R. Sadananda, et al., "The Choice of Neighourhood in Self-Organizing Scheme for VLSI," Proc. Second Int'l. Conf. on Expert Systems for Development; pp. 261-266., Mar. 1994.
D. Choi and S. Park, "Self-Creating and Organizing Neural Networks," IEEE Trans. on Neural Networks, vol. 5(4), pp. 561-575., Jul. 1994.
L. Andrew, "Neuron Splitting for Efficient Feature Map," Proc. 1994 Second Australian and New Zealand Conf. on Intelligent Information Systems, pp. 10-13., Nov. 1994.

Affiliated with

Also associated with

Rating

Neural network for classification of patterns with improved meth 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 for classification of patterns with improved meth, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network for classification of patterns with improved meth will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-965614