Weights Updated Voting for Ensemble of Neural Networks Based Incremental Learning

Authors:
Jianjun Liu;Shengping Xia;Weidong Hu;Wenxian Yu
Affiliations:
State Lab of Automatic Target Recognition, National University of Defense Technology, Changsha, China 410073;State Lab of Automatic Target Recognition, National University of Defense Technology, Changsha, China 410073;State Lab of Automatic Target Recognition, National University of Defense Technology, Changsha, China 410073;State Lab of Automatic Target Recognition, National University of Defense Technology, Changsha, China 410073
Venue:
ISNN '09 Proceedings of the 6th International Symposium on Neural Networks on Advances in Neural Networks
Year:
2009

Citing 8
Cited 0

The Strength of Weak Learnability

Machine Learning
The weighted majority algorithm

Information and Computation
Bagging predictors

Machine Learning
A decision-theoretic generalization of on-line learning and an application to boosting

Journal of Computer and System Sciences - Special issue: 26th annual ACM symposium on the theory of computing & STOC'94, May 23–25, 1994, and second annual Europe an conference on computational learning theory (EuroCOLT'95), March 13–15, 1995
Neural Network Ensembles

IEEE Transactions on Pattern Analysis and Machine Intelligence
Adaptive mixtures of local experts

Neural Computation
Learn++: an incremental learning algorithm for supervised neuralnetworks

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Incremental knowledge acquisition in supervised learning networks

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, an ensemble of neural networks based incremental learning algorithm with weights updated voting is described. The algorithm defines the class kernel function of the training database of the component neural network in the ensemble. The voting weights are updated based on the distance between the test instance and the kernel function. This method can adaptively update the voting weights according to the classification performance of the component neural network on the test pattern and it is more optimal than the stable weights voting strategy. Experimental results show that the ensemble of neural networks based incremental learning algorithm with weights updated voting is more promising than that with stable weights voting rule.