2006/09/22 by Goren Gordon, Gordon, Goren, Uri Einziger-Lowicz +1
Computer Science · #Evolutionary Algorithms and Applications #cs.NE
paper · pdf · doi:10.48550/arxiv.cs/0609125
10 pages, 2 figures
arxiv created 2006/09/22 · arxiv updated 2009/12/01
In this paper we present a novel tool to evaluate problem solving systems. Instead of using a system to solve a problem, we suggest using the problem to evaluate the system. By finding a numerical representation of a problem's complexity, one can implement genetic algorithm to search for the most complex problem the given system can solve. This allows a comparison between different systems that solve the same set of problems. In this paper we implement this approach on pattern recognition neural networks to try and find the most complex pattern a given configuration can solve. The complexity of the pattern is calculated using linguistic complexity. The results demonstrate the power of the problem evolution approach in ranking different neural network configurations according to their pattern recognition abilities. Future research and implementations of this technique are also discussed.