Genetic design of processing elements for path planning networks
暂无分享,去创建一个
The genetic algorithm (GA) is applied to the design of processing elements (PEs) for recurrently connected optimal-path-finding networks. A PE is represented by a parameterized functional expression, and the genetic algorithm searches the function's parameter space to optimize network performance. The GA evaluates each parameterized processing element by placing the PE in a recurrent network, initializing the network with data from an actual terrain, and comparing the relaxed network state with one incorporating the known optimal PE function. For the network topology considered, it was found that a composition of sigmoid terms was able to approximate a discontinuity which existed in the solution PE function. The genetic algorithm employs the principles of the adaptive representation genetic optimizer technique (ARGOT), which increases search speed and efficacy. The present investigation suggests an approach to ANS development which treats the PE function as a design variable
[1] Tariq Samad,et al. Towards the Genetic Synthesisof Neural Networks , 1989, ICGA.
[2] Peter M. Todd,et al. Designing Neural Networks using Genetic Algorithms , 1989, ICGA.
[3] Allon Guez,et al. On the stability, storage capacity, and design of nonlinear continuous neural networks , 1988, IEEE Trans. Syst. Man Cybern..
[4] C. G. Shaefer,et al. The ARGOT Strategy: Adaptive Representation Genetic Optimizer Technique , 1987, ICGA.