Multiple network fusion using fuzzy logic
- 1 March 1995
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 6 (2) , 497-501
- https://doi.org/10.1109/72.363487
Abstract
Multiplayer feedforward networks trained by minimizing the mean squared error and by using a one of c teaching function yield network outputs that estimate posterior class probabilities. This provides a sound basis for combining the results from multiple networks to get more accurate classification. This paper presents a method for combining multiple networks based on fuzzy logic, especially the fuzzy integral. This method non-linearly combines objective evidence, in the form of a network output, with subjective evaluation of the importance of the individual neural networks. The experimental results with the recognition problem of on-line handwriting characters show that the performance of individual networks could be improved significantly.Keywords
This publication has 11 references indexed in Scilit:
- Multiple neural net architectures for character recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Element selection from a fuzzy subset using the fuzzy integralIEEE Transactions on Systems, Man, and Cybernetics, 1993
- Stacked generalizationNeural Networks, 1992
- Learning coefficient dependence on training set sizeNeural Networks, 1992
- Neural Network Classifiers Estimate Bayesian a posteriori ProbabilitiesNeural Computation, 1991
- Adaptive Mixtures of Local ExpertsNeural Computation, 1991
- The state of the art in online handwriting recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Information fusion in computer vision using the fuzzy integralIEEE Transactions on Systems, Man, and Cybernetics, 1990
- Multiple binary decision tree classifiersPattern Recognition, 1990
- Sugeno's fuzzy measure and fuzzy clusteringFuzzy Sets and Systems, 1985