Title :
An efficient algorithm for the binary classification of patterns using MLP-networks
Author :
Fanelli, S. ; Martino, M. Di ; Protasi, M.
Author_Institution :
Dipartimento di Matematica, Roma Univ., Italy
Abstract :
An alternative to the back propagation algorithm for the effective training of multi-layer perceptron (MLP)-networks with binary output is described. The algorithm determines the optimal set of weights by an iterative scheme based on the singular value decomposition (SVD) method and the Fletcher and Reeves version of the conjugate gradient method
Keywords :
feedforward neural nets; iterative methods; learning (artificial intelligence); pattern recognition; MLP-networks; binary classification; binary output; conjugate gradient method; iterative scheme; multi-layer perceptron; pattern classification; singular value decomposition; Computer networks; Gradient methods; Iterative algorithms; Iterative methods; Matrix decomposition; Neural networks; Neurons; Nonlinear equations; Pattern recognition; Singular value decomposition;
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
DOI :
10.1109/ICNN.1993.298683
