Click here to Skip to main content
15,879,096 members
Articles / Artificial Intelligence

Artificial Neural Networks made easy with the FANN library

Rate me:
Please Sign up or sign in to vote.
4.93/5 (46 votes)
28 Aug 2013CPOL24 min read 194K   10.6K   206  
Neural networks are typically associated with specialised applications, developed only by select groups of experts. This misconception has had a highly negative effect on its popularity. Hopefully, the FANN library will help fill this gap.
<!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&nbsp;--&nbsp;Constants representing activation functions.</DIV
><DIV
CLASS="refsect1"
><A
NAME="AEN2034"
></A
><H2
>Description</H2
><P
>&#13;	    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
>&#13;		  <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
>&#13;		  <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
>&#13;		  <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
>&#13;		  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
>&#13;		  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
>&#13;		  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
>&#13;		  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.

License

This article, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)


Written By
Publisher
Poland Poland
Software Developer's Journal (formerly Software 2.0) is a magazine for professional programmers and developers publishing news from the software world and practical articles presenting very interesting ready programming solutions. To read more

Comments and Discussions