📄 x184.html
字号:
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN""http://www.w3.org/TR/html4/loose.dtd"><HTML><HEAD><TITLE>Adjusting Parameters During Training</TITLE><link href="../style.css" rel="stylesheet" type="text/css"><METANAME="GENERATOR"CONTENT="Modular DocBook HTML Stylesheet Version 1.79"><LINKREL="HOME"TITLE="Fast Artificial Neural Network Library"HREF="index.html"><LINKREL="UP"TITLE="Advanced Usage"HREF="c104.html"><LINKREL="PREVIOUS"TITLE="Avoid Over-Fitting"HREF="x181.html"><LINKREL="NEXT"TITLE="Fixed Point Usage"HREF="c189.html"></HEAD><BODYCLASS="section"BGCOLOR="#FFFFFF"TEXT="#000000"LINK="#0000FF"VLINK="#840084"ALINK="#0000FF"><DIVCLASS="NAVHEADER"><TABLESUMMARY="Header navigation table"WIDTH="100%"BORDER="0"CELLPADDING="0"CELLSPACING="0"><TR><THCOLSPAN="3"ALIGN="center">Fast Artificial Neural Network Library</TH></TR><TR><TDWIDTH="10%"ALIGN="left"VALIGN="bottom"><AHREF="x181.html"ACCESSKEY="P">Prev</A></TD><TDWIDTH="80%"ALIGN="center"VALIGN="bottom">Chapter 2. Advanced Usage</TD><TDWIDTH="10%"ALIGN="right"VALIGN="bottom"><AHREF="c189.html"ACCESSKEY="N">Next</A></TD></TR></TABLE><HRALIGN="LEFT"WIDTH="100%"></DIV><DIVCLASS="section"><H1CLASS="section"><ANAME="adv.adj_train">2.6. Adjusting Parameters During Training</A></H1><P> If a very low mean square error is required it can sometimes be a good idea to gradually decrease the learning rate during training, in order to make the adjusting of weights more subtle. If more precision is required, it might also be a good idea to use double precision floats instead of standard floats. </P><P> The threshold activation function is faster than the sigmoid function, but since it is not possible to train with this function, you may wish to consider an alternate approach: </P><P> While training the ANN you could slightly increase the steepness parameter of the sigmoid function. This would make the sigmoid function more steep and make it look more like the threshold function. After this training session you could set the activation function to the threshold function and the ANN would work with this activation function. This approach will not work on all kinds of problems, and has been successfully tested on the XOR function. </P></DIV><DIVCLASS="NAVFOOTER"><HRALIGN="LEFT"WIDTH="100%"><TABLESUMMARY="Footer navigation table"WIDTH="100%"BORDER="0"CELLPADDING="0"CELLSPACING="0"><TR><TDWIDTH="33%"ALIGN="left"VALIGN="top"><AHREF="x181.html"ACCESSKEY="P">Prev</A></TD><TDWIDTH="34%"ALIGN="center"VALIGN="top"><AHREF="index.html"ACCESSKEY="H">Home</A></TD><TDWIDTH="33%"ALIGN="right"VALIGN="top"><AHREF="c189.html"ACCESSKEY="N">Next</A></TD></TR><TR><TDWIDTH="33%"ALIGN="left"VALIGN="top">Avoid Over-Fitting</TD><TDWIDTH="34%"ALIGN="center"VALIGN="top"><AHREF="c104.html"ACCESSKEY="U">Up</A></TD><TDWIDTH="33%"ALIGN="right"VALIGN="top">Fixed Point Usage</TD></TR></TABLE></DIV></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 + -