Title :
Enhancing multi-neural systems through the use of hybrid structures
Author :
Canuto, Anne M P ; Fairhurst, Michael ; Howells, Gareth
Author_Institution :
Informatics & Appl. Mathematic Dept., Univ. Fed. do Rio Grande do Norte, Natal, Brazil
Abstract :
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.
Keywords :
fuzzy neural nets; learning (artificial intelligence); multilayer perceptrons; pattern classification; classification task; fuzzy neural networks; hybrid structures; multi-neural combination; multineural systems; neural experts; Data analysis; Electronic mail; Fuzzy neural networks; Informatics; Mathematics; Multi-layer neural network; Multilayer perceptrons; Neural networks; Pattern recognition; Performance analysis;
Conference_Titel :
Neural Networks, 2003. Proceedings of the International Joint Conference on
Print_ISBN :
0-7803-7898-9
DOI :
10.1109/IJCNN.2003.1223364