A simple method to derive bounds on the size and to train multilayer neural networks

Authors:
M. A. Sartori;P. J. Antsaklis
Affiliations:
Dept. of Electr. Eng., Notre Dame Univ., IN;-
Venue:
IEEE Transactions on Neural Networks
Year:
1991

Citing 0
Cited 9

Geometrical synthesis of MLP neural networks

Neurocomputing
An integrated growing-pruning method for feedforward network training

Neurocomputing
Binary classification using ensemble neural networks and interval neutrosophic sets

Neurocomputing
Constructive approximate interpolation by neural networks

Journal of Computational and Applied Mathematics
Approximate models for nonlinear dynamical systems and their generalization properties

Mathematical and Computer Modelling: An International Journal
Classification of underwater signals using wavelet transforms and neural networks

Mathematical and Computer Modelling: An International Journal
Object recognition using a neural network with optimal feature extraction

Mathematical and Computer Modelling: An International Journal
Letters: Neural network based hybrid computing model for wind speed prediction

Neurocomputing
Review and performance comparison of SVM- and ELM-based classifiers

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new derivation is presented for the bounds on the size of a multilayer neural network to exactly implement an arbitrary training set; namely the training set can be implemented with zero error with two layers and with the number of the hidden-layer neurons equal to #1⩾ p-1. The derivation does not require the separation of the input space by particular hyperplanes, as in previous derivations. The weights for the hidden layer can be chosen almost arbitrarily, and the weights for the output layer can be found by solving #1+1 linear equations. The method presented exactly solves (M), the multilayer neural network training problem, for any arbitrary training set