Complexity search for compressed neural networks
暂无分享,去创建一个
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.
[1] Tom Schaul,et al. Natural Evolution Strategies , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).
[2] Jürgen Schmidhuber,et al. Evolving neural networks in compressed weight space , 2010, GECCO '10.
[3] E. Parzen. On Estimation of a Probability Density Function and Mode , 1962 .
[4] Pieter Abbeel,et al. Learning vehicular dynamics, with application to modeling helicopters , 2005, NIPS.