Getting most out of evolutionary approaches

Evolutionary algorithms (EAs) have been widely used in evolvable hardware. The very term, evolvable hardware, reflects the importance and omnitude of EAs in this field. However, EAs have primarily been used as an optimisation or search tool, which can explore a large and complex space. While success has been demonstrated by EAs in exploring unconventional designs that are hard to reach by human experts, it is interesting to ask the question whether we have fully used all the potentialities of EAs. We argue in this paper that there is rich information in a population which can and should be exploited. The classical approach of evolving the best individual in a population may not be the best one. A truly population-based approach that emphasizes population rather than the best individual can often bring in several important benefits to evolvable hardware, including efficiency, accuracy, adaptiveness, and fault-tolerance.

[1]  Xin Yao,et al.  Making use of population information in evolutionary artificial neural networks , 1998, IEEE Trans. Syst. Man Cybern. Part B.

[2]  Xin Yao,et al.  Evolutionary computation : theory and applications , 1999 .

[3]  Xin Yao,et al.  Evolutionary ensembles with negative correlation learning , 2000, IEEE Trans. Evol. Comput..

[4]  Xin Yao,et al.  A new evolutionary system for evolving artificial neural networks , 1997, IEEE Trans. Neural Networks.

[5]  Xin Yao,et al.  Simultaneous training of negatively correlated neural networks in an ensemble , 1999, IEEE Trans. Syst. Man Cybern. Part B.

[6]  Xin Yao,et al.  A constructive algorithm for training cooperative neural network ensembles , 2003, IEEE Trans. Neural Networks.

[7]  Xin Yao,et al.  Speciation as automatic categorical modularization , 1997, IEEE Trans. Evol. Comput..

[8]  Xin Yao,et al.  Ensemble learning via negative correlation , 1999, Neural Networks.

[9]  X. Yao,et al.  How to Make Best Use of Evolutionary Learning , 1996 .

[10]  Xin Yao,et al.  Every Niching Method has its Niche: Fitness Sharing and Implicit Sharing Compared , 1996, PPSN.

[11]  Xin Yao,et al.  Promises and challenges of evolvable hardware , 1996, IEEE Trans. Syst. Man Cybern. Part C.

[12]  Xin Yao,et al.  From an individual to a population: an analysis of the first hitting time of population-based evolutionary algorithms , 2002, IEEE Trans. Evol. Comput..

[13]  X. Yao,et al.  Scaling up fast evolutionary programming with cooperative coevolution , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[14]  Thomas Bäck,et al.  An Overview of Evolutionary Computation , 1993, ECML.