📄 olgd.htm
字号:
<html><head><title>Netlab Reference Manual olgd</title></head><body><H1> olgd</H1><h2>Purpose</h2>On-line gradient descent optimization.<p><h2>Description</h2><CODE>[net, options, errlog, pointlog] = olgd(net, options, x, t)</CODE> uses on-line gradient descent to find a local minimum of the error function for thenetwork<CODE>net</CODE> computed on the input data <CODE>x</CODE> and target values<CODE>t</CODE>. A log of the error valuesafter each cycle is (optionally) returned in <CODE>errlog</CODE>, and a logof the points visited is (optionally) returned in <CODE>pointlog</CODE>.Because the gradient is computed on-line (i.e. after each pattern)this can be quite inefficient in Matlab.<p>The error function value at final weight vector is returnedin <CODE>options(8)</CODE>.<p>The optional parameters have the following interpretations.<p><CODE>options(1)</CODE> is set to 1 to display error values; also logs error values in the return argument <CODE>errlog</CODE>, and the points visitedin the return argument <CODE>pointslog</CODE>. If <CODE>options(1)</CODE> is set to 0,then only warning messages are displayed. If <CODE>options(1)</CODE> is -1,then nothing is displayed.<p><CODE>options(2)</CODE> is the precision required for the valueof <CODE>x</CODE> at the solution. If the absolute difference betweenthe values of <CODE>x</CODE> between two successive steps is less than<CODE>options(2)</CODE>, then this condition is satisfied.<p><CODE>options(3)</CODE> is the precision required of the objectivefunction at the solution. If the absolute difference between theerror functions between two successive steps is less than<CODE>options(3)</CODE>, then this condition is satisfied.Both this and the previous condition must besatisfied for termination. Note that testing the function value at eachiteration roughly halves the speed of the algorithm.<p><CODE>options(5)</CODE> determines whether the patterns are sampled randomlywith replacement. If it is 0 (the default), then patterns are sampledin order.<p><CODE>options(6)</CODE> determines if the learning rate decays. If it is 1then the learning rate decays at a rate of <CODE>1/t</CODE>. If it is 0(the default) then the learning rate is constant.<p><CODE>options(9)</CODE> should be set to 1 to check the user defined gradientfunction.<p><CODE>options(10)</CODE> returns the total number of function evaluations (includingthose in any line searches).<p><CODE>options(11)</CODE> returns the total number of gradient evaluations.<p><CODE>options(14)</CODE> is the maximum number of iterations (passes throughthe complete pattern set); default 100.<p><CODE>options(17)</CODE> is the momentum; default 0.5.<p><CODE>options(18)</CODE> is the learning rate; default 0.01.<p><h2>Examples</h2>The following example performs on-line gradient descent on an MLP withrandom sampling from the pattern set.<PRE>net = mlp(5, 3, 1, 'linear');options = foptions;options(18) = 0.01;options(5) = 1;net = olgd(net, options, x, t);</PRE><p><h2>See Also</h2><CODE><a href="graddesc.htm">graddesc</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 + -