Enhancing multi-neural systems through the use of hybrid structures

This paper investigates the performance of multi-neural systems, focusing on the benefits that can be gained when integrating different types of neural experts (hybrid multi-neural system). An empirical evaluation shows that the integration of different types of neural networks leads to an improvement in performance in a practical classification task for a range of combination methods.

[1]  Xin Yao,et al.  Ensemble learning via negative correlation , 1999, Neural Networks.

[2]  A.M.P. Canuto,et al.  A generalization process for weightless neurons , 1995 .

[3]  Anne M. P. Canuto,et al.  An Investigation of the Effects of Variable Vigilance within the RePART Neuro-Fuzzy Network , 2000, J. Intell. Robotic Syst..

[4]  Sung-Bae Cho,et al.  Multiple network fusion using fuzzy logic , 1995, IEEE Trans. Neural Networks.

[5]  Sankar K. Pal,et al.  Multilayer perceptron, fuzzy sets, and classification , 1992, IEEE Trans. Neural Networks.

[6]  Canuto,et al.  Fuzzy multi-layer perceptron for binary pattern recognition , 1999 .

[7]  Sung-Bae Cho,et al.  Pattern recognition with neural networks combined by genetic algorithm , 1999, Fuzzy Sets Syst..

[8]  Lars Kai Hansen,et al.  Neural Network Ensembles , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Volker Tresp,et al.  Combining Estimators Using Non-Constant Weighting Functions , 1994, NIPS.

[10]  Prampero,et al.  Classifier combination for vehicle silhouettes recognition , 1999 .

[11]  Anne M. P. Canuto,et al.  RePART: A Modified Fuzzy ARTMAP for Pattern Recognition , 1999, Fuzzy Days.

[12]  M. Kamel,et al.  Voting schemes for cooperative neural network classifiers , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[13]  Sargur N. Srihari,et al.  Decision Combination in Multiple Classifier Systems , 1994, IEEE Trans. Pattern Anal. Mach. Intell..