<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN"> <HTML ><HEAD ><TITLE >Training Error Functions</TITLE ><link href="../style.css" rel="stylesheet" type="text/css"><META NAME="GENERATOR" CONTENT="Modular DocBook HTML Stylesheet Version 1.7"><LINK REL="HOME" TITLE="Fast Artificial Neural Network Library" HREF="index.html"><LINK REL="UP" TITLE="Constants" HREF="x1994.html"><LINK REL="PREVIOUS" TITLE="Activation Functions" HREF="r2030.html"><LINK REL="NEXT" TITLE="Error Codes" HREF="r2099.html"></HEAD ><BODY CLASS="refentry" BGCOLOR="#FFFFFF" TEXT="#000000" LINK="#0000FF" VLINK="#840084" ALINK="#0000FF" ><DIV CLASS="NAVHEADER" ><TABLE SUMMARY="Header navigation table" WIDTH="100%" BORDER="0" CELLPADDING="0" CELLSPACING="0" ><TR ><TH COLSPAN="3" ALIGN="center" >Fast Artificial Neural Network Library</TH ></TR ><TR ><TD WIDTH="10%" ALIGN="left" VALIGN="bottom" ><A HREF="r2030.html" ACCESSKEY="P" >Prev</A ></TD ><TD WIDTH="80%" ALIGN="center" VALIGN="bottom" ></TD ><TD WIDTH="10%" ALIGN="right" VALIGN="bottom" ><A HREF="r2099.html" ACCESSKEY="N" >Next</A ></TD ></TR ></TABLE ><HR ALIGN="LEFT" WIDTH="100%"></DIV ><H1 ><A NAME="api.sec.constants.errorfunc" ></A >Training Error Functions</H1 ><DIV CLASS="refnamediv" ><A NAME="AEN2078" ></A ><H2 >Name</H2 >Training Error Functions -- Constants representing errors functions.</DIV ><DIV CLASS="refsect1" ><A NAME="AEN2081" ></A ><H2 >Description</H2 ><P > These constants represent the error functions used when calculating the error during training. </P ><P > The training error function used is chosen by the <A HREF="r1170.html" ><CODE CLASS="function" >fann_set_train_error_function</CODE ></A > function. The default training error function is <CODE CLASS="constant" >FANN_ERRORFUNC_TANH</CODE >. </P ><P ></P ><DIV CLASS="variablelist" ><P ><B >Constants</B ></P ><DL ><DT >FANN_ERRORFUNC_LINEAR</DT ><DD ><P > The basic linear error function which simply calculates the error as the difference between the real output and the desired output. </P ></DD ><DT >FANN_ERRORFUNC_TANH</DT ><DD ><P > The tanh error function is an error function that makes large deviations stand out, by altering the error value used when training the network. The idea behind this is that it is worse to have 1 output that misses the target by 100%, than having 10 outputs that misses the target by 10%. </P ><P > This is the default error function and it is usually better. It can however give poor results with high learning rates. </P ></DD ></DL ></DIV ></DIV ><DIV CLASS="NAVFOOTER" ><HR ALIGN="LEFT" WIDTH="100%"><TABLE SUMMARY="Footer navigation table" WIDTH="100%" BORDER="0" CELLPADDING="0" CELLSPACING="0" ><TR ><TD WIDTH="33%" ALIGN="left" VALIGN="top" ><A HREF="r2030.html" ACCESSKEY="P" >Prev</A ></TD ><TD WIDTH="34%" ALIGN="center" VALIGN="top" ><A HREF="index.html" ACCESSKEY="H" >Home</A ></TD ><TD WIDTH="33%" ALIGN="right" VALIGN="top" ><A HREF="r2099.html" ACCESSKEY="N" >Next</A ></TD ></TR ><TR ><TD WIDTH="33%" ALIGN="left" VALIGN="top" >Activation Functions</TD ><TD WIDTH="34%" ALIGN="center" VALIGN="top" ><A HREF="x1994.html" ACCESSKEY="U" >Up</A ></TD ><TD WIDTH="33%" ALIGN="right" VALIGN="top" >Error Codes</TD ></TR ></TABLE ></DIV ></BODY ></HTML >
By viewing downloads associated with this article you agree to the Terms of Service and the article's licence.
If a file you wish to view isn't highlighted, and is a text file (not binary), please let us know and we'll add colourisation support for it.
This article, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)