Abstract | ||
---|---|---|
This paper, with an aim at improving neural networks' generalization performance, proposes an effective neural network ensemble approach with two novel ideas. One is to apply neural networks' output sensitivity as a measure to evaluate neural networks' output diversity at the inputs near training samples so as to be able to select diverse individuals from a pool of well-trained neural networks; the other is to employ a learning mechanism to assign complementary weights for the combination of the selected individuals. Experimental results show that the proposed approach could construct a neural network ensemble with better generalization performance than that of each individual in the ensemble combining with all the other individuals, and than that of the ensembles with simply averaged weights. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/TNNLS.2013.2246578 | IEEE Trans. Neural Netw. Learning Syst. |
Keywords | Field | DocType |
generalization performance,sensitivity,fusion,training samples,neural network ensemble approach,neural network output sensitivity,learning (artificial intelligence),diversity ensemble learning,well-trained neural network,simply averaged weights,neural nets,neural network ensemble,learning artificial intelligence,neural networks,boosting | Feedforward neural network,Pattern recognition,Computer science,Stochastic neural network,Recurrent neural network,Probabilistic neural network,Types of artificial neural networks,Time delay neural network,Artificial intelligence,Deep learning,Artificial neural network,Machine learning | Journal |
Volume | Issue | ISSN |
24 | 6 | 2162-2388 |
Citations | PageRank | References |
19 | 0.73 | 27 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jing Yang | 1 | 19 | 0.73 |
Xiaoqin Zeng | 2 | 407 | 32.97 |
Shuiming Zhong | 3 | 79 | 7.30 |
Shengli Wu | 4 | 370 | 33.55 |