|
<!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.