Acceleration of Evolutionary Image Filter Design Using Coevolution in Cartesian GP

The aim of this work is to accelerate the task of evolutionary image filter design using coevolution of candidate filters and training vectors subsets. Two coevolutionary methods are implemented and compared for this task in the framework of Cartesian Genetic Programming (CGP). Experimental results show that only 15---20% of original training vectors are needed to find an image filter which provides the same quality of filtering as the best filter evolved using the standard CGP which utilizes the whole training set. Moreover, the median time of evolution was reduced 2.99 times in comparison with the standard CGP.

[1]  Julian Francis Miller.  Cartesian Genetic Programming , 2011, Cartesian Genetic Programming.

[2]  John R. Koza,et al.  Routine human-competitive machine intelligence by means of genetic programming , 2004, SPIE Optics + Photonics.

[3]  Wolfgang Banzhaf,et al.  Image Processing and CGP , 2011, Cartesian Genetic Programming.

[4]  Gary L. Haith,et al.  Comparing a coevolutionary genetic algorithm for multiobjective optimization , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[5]  Jin Wang,et al.  Design and implementation of a virtual reconfigurable architecture for different applications of intrinsic evolvable hardware , 2008, IET Comput. Digit. Tech..

[6]  Wolfgang Banzhaf,et al.  Hardware Acceleration for CGP: Graphics Processing Units , 2011, Cartesian Genetic Programming.

[7]  Lukas Sekanina,et al.  Hardware Accelerator of Cartesian Genetic Programming with Multiple Fitness Units , 2012 .

[8]  Lukás Sekanina,et al.  Coevolution in Cartesian Genetic Programming , 2012, EuroGP.

[9]  John R. Koza,et al.  Genetic Programming IV: Routine Human-Competitive Machine Intelligence , 2003 .

[10]  W. Daniel Hillis,et al.  Co-evolving parasites improve simulated evolution as an optimization procedure , 1990 .

[11]  Paulien Hogeweg,et al.  Evolutionary Consequences of Coevolving Targets , 1997, Evolutionary Computation.

[12]  Hod Lipson,et al.  Coevolution of Fitness Predictors , 2008, IEEE Transactions on Evolutionary Computation.

[13]  Richard K. Belew,et al.  New Methods for Competitive Coevolution , 1997, Evolutionary Computation.