Title :
Basis vector analyses of back-propagation neural networks
Author :
Chen, Mu-Song ; Manry, Michael T.
Author_Institution :
Dept. of Electr. Eng., Texas Univ., Arlington, TX, USA
Abstract :
Develops a polynomial basis function approach for modeling BP (backpropagation) neural networks. This method leads directly to a constructive proof of the BP approximation theorem. In addition, the basis vector approach provides a means to synthesize the BP neural network output as a polynomial function. An algorithm for pruning the useless basis vectors is also demonstrated
Keywords :
backpropagation; neural nets; polynomials; BP approximation theorem; back-propagation neural networks; basis vector approach; constructive proof; polynomial function; Convergence; Filtering; Joining processes; Network topology; Neural networks; Polynomials; Taylor series;
Conference_Titel :
Circuits and Systems, 1991., Proceedings of the 34th Midwest Symposium on
Conference_Location :
Monterey, CA
Print_ISBN :
0-7803-0620-1
DOI :
10.1109/MWSCAS.1991.252222
