Structure optimization of neural networks for evolutionary design optimization

We study the use of neural networks as approximate models for the fitness evaluation in evolutionary design optimization. To improve the quality of the neural network models, structure optimization of these networks is performed with respect to two different criteria: One is the commonly used approximation error with respect to all available data, and the other is the ability of the networks to learn different problems of a common class of problems fast and with high accuracy. Simulation results from turbine blade optimizations using the structurally optimized neural network models are presented to show that the performance of the models can be improved significantly through structure optimization.

[1]  Nikolaus Hansen,et al.  Completely Derandomized Self-Adaptation in Evolution Strategies , 2001, Evolutionary Computation.

[2]  Toshiyuki Arima,et al.  A Numerical Investigation of Transonic Axial Compressor Rotor Flow Using a Low Reynolds Number k-ε Turbulence Model , 1997 .

[3]  M. Husken,et al.  Optimization for problem classes-neural networks that learn to learn , 2000, 2000 IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks. Proceedings of the First IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks (Cat. No.00.

[4]  L. Darrell Whitley,et al.  Lamarckian Evolution, The Baldwin Effect and Function Optimization , 1994, PPSN.

[5]  Marc Toussaint,et al.  Task-dependent evolution of modularity in neural networks , 2002 .

[6]  Natalia Alexandrov,et al.  Multidisciplinary design optimization : state of the art , 1997 .

[7]  Christian Igel,et al.  Empirical evaluation of the improved Rprop learning algorithms , 2003, Neurocomputing.

[8]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[9]  Yaochu Jin,et al.  Managing approximate models in evolutionary aerodynamic design optimization , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[10]  Bernhard Sendhoff,et al.  Optimisation of a Stator Blade Used in a Transonic Compressor Cascade with Evolution Strategies , 2000 .

[11]  Max F. Meyer,et al.  The Proof and Measurement of Association between Two Things. , 1904 .

[12]  Bernhard Sendhoff,et al.  Fitness Approximation In Evolutionary Computation - a Survey , 2002, GECCO.

[13]  X. Yao.  Evolving Artificial Neural Networks , 1999 .

[14]  T. Arima,et al.  A Numerical Investigation of Transonic Axial Compressor Rotor Flow Using a Low-Reynolds-Number k–ε Turbulence Model , 1999 .

[15]  Bernhard Sendhoff,et al.  Evolutionary Optimization for Problem Classes with Lamarckian Inheritance , 2000 .

[16]  Bernhard Sendhoff,et al.  On Evolutionary Optimization with Approximate Fitness Functions , 2000, GECCO.