Committee C-mantec: a probabilistic constructive neural network

Authors:
Jose Luis Subirats;Rafael Marcos Luque-Baena;Daniel Urda;Francisco Ortega-Zamorano;Jose Manuel Jerez;Leonardo Franco
Affiliations:
Department of Computer Science, University of Málaga, Málaga, Spain;Department of Computer Science, University of Málaga, Málaga, Spain;Department of Computer Science, University of Málaga, Málaga, Spain;Department of Computer Science, University of Málaga, Málaga, Spain;Department of Computer Science, University of Málaga, Málaga, Spain;Department of Computer Science, University of Málaga, Málaga, Spain
Venue:
IWANN'13 Proceedings of the 12th international conference on Artificial Neural Networks: advances in computational intelligence - Volume Part I
Year:
2013

Citing 6
Cited 0

What size net gives valid generalization?

Neural Computation
A “thermal” perceptron learning rule

Neural Computation
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
An empirical evaluation of constructive neural network algorithms in classification tasks

International Journal of Innovative Computing and Applications
Neural network architecture selection: can function complexity help?

Neural Processing Letters
C-Mantec: A novel constructive neural network algorithm incorporating competition between neurons

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

C-Mantec is a recently introduced constructive algorithm that generates compact neural architectures with good generalization abilities. Nevertheless, it produces a discrete output value and this might be a drawback in certain situations. We propose in this work two approaches in order to obtain a continuous output network such as the output can be interpreted as the probability of a given pattern to belong to one of the output classes. The CC-Mantec approach utilizes a committee strategy and the results obtained both with the XOR Boolean function and with a set of benchmark functions shows the suitability of the approach, as an improvement over the standard C-Mantec algorithm is obtained in almost all cases.