Click here to Skip to main content
15,886,199 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 194.4K   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
>Avoid Over-Fitting</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="Advanced Usage"
HREF="c104.html"><LINK
REL="PREVIOUS"
TITLE="Training and Testing"
HREF="x161.html"><LINK
REL="NEXT"
TITLE="Adjusting Parameters During Training"
HREF="x184.html"></HEAD
><BODY
CLASS="section"
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="x161.html"
ACCESSKEY="P"
>Prev</A
></TD
><TD
WIDTH="80%"
ALIGN="center"
VALIGN="bottom"
>Chapter 2. Advanced Usage</TD
><TD
WIDTH="10%"
ALIGN="right"
VALIGN="bottom"
><A
HREF="x184.html"
ACCESSKEY="N"
>Next</A
></TD
></TR
></TABLE
><HR
ALIGN="LEFT"
WIDTH="100%"></DIV
><DIV
CLASS="section"
><H1
CLASS="section"
><A
NAME="adv.over_fit"
>2.5. Avoid Over-Fitting</A
></H1
><P
>&#13;        With the knowledge of how to train and test an ANN, a new approach to training can be introduced. If too much training is applied to a set of data, the
	ANN will eventually over-fit, meaning that it will be fitted precisely to this set of training data and thereby loosing generalization. It is often a
	good idea to test, how good an ANN performs on data that it has not seen before. Testing with data not seen before, can be done while training, to see
	how much training is required in order to perform well without over-fitting. The testing can either be done by hand, or an automatic test can be applied,
	which stops the training when the mean square error of the test data is not improving anymore.
      </P
></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="x161.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="x184.html"
ACCESSKEY="N"
>Next</A
></TD
></TR
><TR
><TD
WIDTH="33%"
ALIGN="left"
VALIGN="top"
>Training and Testing</TD
><TD
WIDTH="34%"
ALIGN="center"
VALIGN="top"
><A
HREF="c104.html"
ACCESSKEY="U"
>Up</A
></TD
><TD
WIDTH="33%"
ALIGN="right"
VALIGN="top"
>Adjusting Parameters During Training</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