Title :
A learning rule in the Chebyshev norm for multilayer perceptrons
Author :
Burrascano, P. ; Lucci, P.
Author_Institution :
INFO-COM Dept., Roma Univ., Italy
Abstract :
An L∞ version of the back-propagation paradigm is proposed. A comparison between the L2 and the L∞ paradigms is presented, taking into account computational cost and speed of convergence. It is shown how the learning process can be formulated as an optimization problem. Experimental results from two test cases of the convergence of the L ∞ algorithm are presented
Keywords :
learning systems; neural nets; optimisation; Chebyshev norm; back-propagation paradigm; computational cost; convergence; learning process; learning rule; multilayer perceptrons; optimization problem; test cases; Approximation error; Chebyshev approximation; Feedforward neural networks; Intelligent networks; Multi-layer neural network; Multilayer perceptrons; Neural networks; Neurons; Probability density function; Testing;
Conference_Titel :
Circuits and Systems, 1990., IEEE International Symposium on
Conference_Location :
New Orleans, LA
DOI :
10.1109/ISCAS.1990.111987
