Negatively correlated neural networks for classification |
| |
Authors: | Yong Liu Xin Yao |
| |
Affiliation: | (1) Evolvable Systems Laboratory, Computer Science Division, Electrotechnical Laboratory, 1-1-4 Umezono, 305-8568 Tsukuba, Ibaraki, Japan;(2) School of Computer Science, The University of Birmingham, Edgbaston, Birmingham, U.K. |
| |
Abstract: | This paper presents a new algorithm for designing neural network ensembles for classification problems with noise. The idea
behind this new algorithm is to encourage different individual networks in an ensemble to learn different parts or aspects
of the training data so that the whole ensemble can learn the whole training data better. Negatively correlated neural networks
are trained with a novel correlation penalty term in the error function to encourage such specialization. In our algorithm,
individual networks are trained simultaneously rather than independently or sequentially. This provides an opportunity for
different networks to interact with each other and to specialize. Experiments on two real-world problems demonstrate that
the new algorithm can produce neural network ensembles with good generalization ability.
This work was presented, in part, at the Third International Symposium on Artificial Life and Robotics, Oita, Japan January
19–21, 1998 |
| |
Keywords: | Neural network ensembles Learning Generalization Bias Variance |
本文献已被 SpringerLink 等数据库收录! |
|