DocumentCode :
1747759
Title :
Evolving a cooperative population of neural networks by minimizing mutual information
Author :
Liu, Yong ; Yao, Xin ; Zhao, Qiangfu ; Higuchi, Tetsuya
Author_Institution :
Aizu Univ., Fukushima, Japan
Volume :
1
fYear :
2001
fDate :
2001
Firstpage :
384
Abstract :
Evolutionary ensembles with negative correlation learning (EENCL) is an evolutionary learning system for learning and designing neural network ensembles (Liu et al., 2000). The fitness sharing used in EENCL was based on the idea of “covering” the same training patterns by shared individuals. This paper explores connection between fitness sharing and information concept, and introduces mutual information into EENCL. Through minimization of mutual information, a diverse and cooperative population of neural networks can be evolved by EENCL. The effectiveness of such evolutionary learning approach was tested on two real-world problems
Keywords :
evolutionary computation; learning (artificial intelligence); neural nets; EENCL; cooperative population; evolutionary ensembles; evolutionary learning system; fitness sharing; mutual information minimization; negative correlation learning; neural networks; training patterns; Algorithm design and analysis; Design optimization; Entropy; Laboratories; Learning systems; Mutual information; Neural networks; Robustness; Testing; Training data;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Evolutionary Computation, 2001. Proceedings of the 2001 Congress on
Conference_Location :
Seoul
Print_ISBN :
0-7803-6657-3
Type :
conf
DOI :
10.1109/CEC.2001.934416
Filename :
934416
Link To Document :
بازگشت