RBF神经网络英文课件.pdfVIP

Radial Basis Function Networks: Algorithms Introduction to Neural Networks : Lecture 13 © John A. Bullinaria, 2004 1. The RBF Mapping 2. The RBF Network Architecture 3. Computational Power of RBF Networks 4. Training an RBF Network 5. Unsupervised Optimization of the Basis Functions 6. Finding the Output Weights The Radial Basis Function (RBF) Mapping We are working within the standard framework of function approximation. We have a set of N data points in a multi-dimensional space such that every D dimensional input vector xp = {x p : i = 1,...,D} has a corresponding K dimensional target output tp = {tp : k = 1,...,K }. i k The target outputs will generally be generated by some underlying functions g (x) plus k random noise. The goal is to approximate the g (x) with functions y (x) of the form k k M yk (x) = ∑ wkjφj (x) j =0 We shall concentrate on the case of Gaussian basis functions  x − µµj 2  φ (x) = exp − j  2   2σ   j 