Combined orthogonal vector and pseudo-inverse approach for robust pattern recognition

Document Type

Conference Proceeding

Publication Date

1-1-1992

Abstract

A neural-based orthogonal vector with a pseudo-inverse approach for pattern recognition is presented. A method for generating N orthogonal vectors for an N-neuron network is also presented. This approach converges the input to the corresponding orthogonal vector representing the prototype vector. Moreover, it can restore an image to the original image and thus has error recovery capability. Patterns with 20% error were recognized, using English capital latters as an example. The robustness of this approach is obvious.

Identifier

85067336023 (Scopus)

ISBN

[0780308093, 9780780308091]

Publication Title

Proceedings 1992 Rnns IEEE Symposium on Neuroinformatics and Neurocomputers Rnns 1992

External Full Text Location

https://doi.org/10.1109/RNNS.1992.268629

First Page

881

Last Page

887

This document is currently not available here.

Share

COinS