Sigmoids Distinguish More Efficiently Than Heavisides
暂无分享,去创建一个
Every dichotomy on a 2k-point set in ℝN can be implemented by a neural net with a single hidden layer containing k sigmoidal neurons. If the neurons were of a hardlimiter (Heaviside) type, 2k 1 would be in general needed.
[1] George Cybenko,et al. Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..
[2] Kurt Hornik,et al. Multilayer feedforward networks are universal approximators , 1989, Neural Networks.