|
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<HTML
><HEAD
><TITLE
>Activation 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="Training algorithms"
HREF="r1996.html"><LINK
REL="NEXT"
TITLE="Training Error Functions"
HREF="r2077.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="r1996.html"
ACCESSKEY="P"
>Prev</A
></TD
><TD
WIDTH="80%"
ALIGN="center"
VALIGN="bottom"
></TD
><TD
WIDTH="10%"
ALIGN="right"
VALIGN="bottom"
><A
HREF="r2077.html"
ACCESSKEY="N"
>Next</A
></TD
></TR
></TABLE
><HR
ALIGN="LEFT"
WIDTH="100%"></DIV
><H1
><A
NAME="api.sec.constants.activation"
></A
>Activation Functions</H1
><DIV
CLASS="refnamediv"
><A
NAME="AEN2031"
></A
><H2
>Name</H2
>Activation Functions -- Constants representing activation functions.</DIV
><DIV
CLASS="refsect1"
><A
NAME="AEN2034"
></A
><H2
>Description</H2
><P
> These constants represent the activation functions available within the fann library.
The list will grow over time, but probably not shrink.
</P
><P
></P
><DIV
CLASS="variablelist"
><P
><B
>Constants</B
></P
><DL
><DT
>FANN_THRESHOLD</DT
><DD
><P
> <SPAN
CLASS="emphasis"
><I
CLASS="emphasis"
>Execution only</I
></SPAN
> - Threshold activation function.
</P
><P
> This activation function gives output that is either 0 or 1.</P
></DD
><DT
>FANN_THRESHOLD_SYMMETRIC</DT
><DD
><P
> <SPAN
CLASS="emphasis"
><I
CLASS="emphasis"
>Execution only</I
></SPAN
> - Threshold activation function.
</P
><P
> This activation function gives output that is either -1 or 1.</P
></DD
><DT
>FANN_LINEAR</DT
><DD
><P
> <SPAN
CLASS="emphasis"
><I
CLASS="emphasis"
>Can not be used in fixed point</I
></SPAN
> - Linear activation function.
</P
><P
> This activation function gives output that is unbounded.</P
></DD
><DT
>FANN_SIGMOID</DT
><DD
><P
> Sigmoid activation function. One of the most used activation functions.
</P
><P
> This activation function gives output that is between 0 and 1.</P
></DD
><DT
>FANN_SIGMOID_STEPWISE</DT
><DD
><P
> Stepwise linear approximation to sigmoid. Faster than sigmoid but a bit less precise.
</P
><P
> This activation function gives output that is between 0 and 1.</P
></DD
><DT
>FANN_SIGMOID_SYMMETRIC</DT
><DD
><P
> Symmetric sigmoid activation function, AKA tanh. One of the most used activation functions.
</P
><P
> This activation function gives output that is between -1 and 1.</P
></DD
><DT
>FANN_SIGMOID_SYMMETRIC_STEPWISE</DT
><DD
><P
> Stepwise linear approximation to symmetric sigmoid. Faster than symmetric sigmoid but a bit less precise.
</P
><P
> This activation function gives output that is between -1 and 1.</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="r1996.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="r2077.html"
ACCESSKEY="N"
>Next</A
></TD
></TR
><TR
><TD
WIDTH="33%"
ALIGN="left"
VALIGN="top"
>Training algorithms</TD
><TD
WIDTH="34%"
ALIGN="center"
VALIGN="top"
><A
HREF="x1994.html"
ACCESSKEY="U"
>Up</A
></TD
><TD
WIDTH="33%"
ALIGN="right"
VALIGN="top"
>Training Error Functions</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.