rbfbkp.htm
来自「这是包含pca和ppca等诸多源程序的工具箱」· HTM 代码 · 共 51 行
HTM
51 行
<html><head><title>Netlab Reference Manual rbfbkp</title></head><body><H1> rbfbkp</H1><h2>Purpose</h2>Backpropagate gradient of error function for RBF network.<p><h2>Synopsis</h2><PRE>g = rbfbkp(net, x, z, n2, deltas)</PRE><p><h2>Description</h2><CODE>g = rbfbkp(net, x, z, n2, deltas)</CODE> takes a network data structure<CODE>net</CODE> together with a matrix <CODE>x</CODE> of input vectors, a matrix <CODE>z</CODE> of hidden unit activations, a matrix <CODE>n2</CODE> of the squareddistances between centres and inputs, and a matrix <CODE>deltas</CODE> of the gradient of the error function with respect to the values of theoutput units (i.e. the summed inputs to the output units, before theactivation function is applied). The return value is the gradient<CODE>g</CODE> of the error function with respect to the networkweights. Each row of <CODE>x</CODE> corresponds to one input vector.<p>This function is provided so that the common backpropagation algorithmcan be used by RBF network models to computegradients for the output values (in <CODE>rbfderiv</CODE>) as well as standard errorfunctions.<p><h2>See Also</h2><CODE><a href="rbf.htm">rbf</a></CODE>, <CODE><a href="rbfgrad.htm">rbfgrad</a></CODE>, <CODE><a href="rbfderiv.htm">rbfderiv</a></CODE><hr><b>Pages:</b><a href="index.htm">Index</a><hr><p>Copyright (c) Ian T Nabney (1996-9)</body></html>
⌨️ 快捷键说明
复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?