📄 mlpprior.htm
字号:
<html><head><title>Netlab Reference Manual mlpprior</title></head><body><H1> mlpprior</H1><h2>Purpose</h2>Create Gaussian prior for mlp.<p><h2>Synopsis</h2><PRE>prior = mlpprior(nin, nhidden, nout, aw1, ab1, aw2, ab2)</PRE><p><h2>Description</h2><CODE>prior = mlpprior(nin, nhidden, nout, aw1, ab1, aw2, ab2)</CODE> generates a data structure<CODE>prior</CODE>, with fields <CODE>prior.alpha</CODE> and <CODE>prior.index</CODE>, whichspecifies a Gaussian prior distribution for the network weights in atwo-layer feedforward network. Two different cases are possible. Inthe first case, <CODE>aw1</CODE>, <CODE>ab1</CODE>, <CODE>aw2</CODE> and <CODE>ab2</CODE> are allscalars and represent the regularization coefficients for four groupsof parameters in the network corresponding to first-layer weights,first-layer biases, second-layer weights, and second-layer biasesrespectively. Then <CODE>prior.alpha</CODE> represents a column vector oflength 4 containing the parameters, and <CODE>prior.index</CODE> is a matrixspecifying which weights belong in each group. Each column has oneelement for each weight in the matrix, using the standard ordering asdefined in <CODE>mlppak</CODE>, and each element is 1 or 0 according towhether the weight is a member of the corresponding group or not. Inthe second case the parameter <CODE>aw1</CODE> is a vector of length equal tothe number of inputs in the network, and the corresponding matrix<CODE>prior.index</CODE> now partitions the first-layer weights into groupscorresponding to the weights fanning out of each input unit. This prior is appropriate for the technique of automatic relevancedetermination. <p><h2>See Also</h2><CODE><a href="mlp.htm">mlp</a></CODE>, <CODE><a href="mlperr.htm">mlperr</a></CODE>, <CODE><a href="mlpgrad.htm">mlpgrad</a></CODE>, <CODE><a href="evidence.htm">evidence</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
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -