Evolving a cooperative population of neural networks by minimizing mutual information

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