In this paper, we introduce a method, called Compressed Network Complexity Search (CNCS), for automatically determining the complexity of compressed networks (neural networks encoded indirectly by Fourier-type coefficients) that favors parsimonious solutions. CNCS maintains a probability distribution over complexity classes that it uses to select which class to optimize. Class probabilities are adapted based on their expected fitness, starting with a prior biased toward the simplest networks. Experiments on a challenging non-linear version of the helicopter hovering task, show that the method consistently finds simple solutions. Copyright is held by the author/owner(s).
|Original language||English (US)|
|Title of host publication||GECCO'12 - Proceedings of the 14th International Conference on Genetic and Evolutionary Computation Companion|
|Publisher||Association for Computing Machinery|
|Number of pages||2|
|State||Published - Jan 1 2012|