Downloads: Artificial Neural Networks made easy with the FANN library

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<HTML
><HEAD
><TITLE
>Fixed Point Usage</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="PREVIOUS"
TITLE="Adjusting Parameters During Training"
HREF="x184.html"><LINK
REL="NEXT"
TITLE="Running a Fixed Point ANN"
HREF="x203.html"></HEAD
><BODY
CLASS="chapter"
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="x184.html"
ACCESSKEY="P"
>Prev</A
></TD
><TD
WIDTH="80%"
ALIGN="center"
VALIGN="bottom"
></TD
><TD
WIDTH="10%"
ALIGN="right"
VALIGN="bottom"
><A
HREF="x203.html"
ACCESSKEY="N"
>Next</A
></TD
></TR
></TABLE
><HR
ALIGN="LEFT"
WIDTH="100%"></DIV
><DIV
CLASS="chapter"
><H1
><A
NAME="fixed"
></A
>Chapter 3. Fixed Point Usage</H1
><P
>&#13;      It is possible to run the ANN with fixed point numbers (internally represented as integers). This option is only intended for use on computers with no
      floating point processor, for example, the iPAQ, but a minor performance enhancement can also be seen on most modern computers
      [<A
HREF="b3048.html#bib.IDS_2000"
><I
>IDS, 2000</I
></A
>].
    </P
><DIV
CLASS="section"
><H1
CLASS="section"
><A
NAME="fixed.train"
>3.1. Training a Fixed Point ANN</A
></H1
><P
>&#13;        The ANN cannot be trained in fixed point, which is why the training part is basically the same as for floating point numbers. The only difference is that
	you should save the ANN as fixed point. This is done by the <A
HREF="r494.html"
><CODE
CLASS="function"
>fann_save_to_fixed</CODE
></A
>
	function. This function saves a fixed point version of the ANN, but it also does some analysis, in order to find out where the decimal point should be.
	The result of this analysis is returned from the function.
      </P
><P
>&#13;	The decimal point returned from the function is an indicator of, how many bits is used for the fractional part of the fixed point numbers. If this number
	is negative, there will most likely be integer overflow when running the library with fixed point numbers and this should be avoided. Furthermore, if
	the decimal point is too low (e.g. lower than 5), it is probably not a good idea to use the fixed point version.
      </P
><P
>&#13;	Please note, that the inputs to networks that should be used in fixed point should be between -1 and 1.
      </P
><DIV
CLASS="example"
><A
NAME="example.train_fixed"
></A
><P
><B
>Example 3-1. An example of a program written to support training in both fixed point and floating point numbers</B
></P
><PRE
CLASS="programlisting"
>&#13;
#include "fann.h"
#include &#60;stdio.h&#62;

int main()
{
	fann_type *calc_out;
	const float connection_rate = 1;
	const float learning_rate = 0.7;
	const unsigned int num_input = 2;
	const unsigned int num_output = 1;
	const unsigned int num_layers = 3;
	const unsigned int num_neurons_hidden = 4;
	const float desired_error = 0.001;
	const unsigned int max_iterations = 20000;
	const unsigned int iterations_between_reports = 100;
	struct fann *ann;
	struct fann_train_data *data;
	
	unsigned int i = 0;
	unsigned int decimal_point;

	printf("Creating network.\n");

	ann = fann_create(connection_rate, learning_rate, num_layers,
		num_input,
		num_neurons_hidden,
		num_output);

	printf("Training network.\n");

	data = fann_read_train_from_file("xor.data");

	fann_train_on_data(ann, data, max_iterations, iterations_between_reports, desired_error);

	printf("Testing network.\n");

	for(i = 0; i &#60; data-&#62;num_data; i++){
		calc_out = fann_run(ann, data-&#62;input[i]);
		printf("XOR test (%f,%f) -&#62; %f, should be %f, difference=%f\n",
		data-&#62;input[i][0], data-&#62;input[i][1], *calc_out, data-&#62;output[i][0], fann_abs(*calc_out - data-&#62;output[i][0]));
	}
	
	printf("Saving network.\n");

	fann_save(ann, "xor_float.net");

	decimal_point = fann_save_to_fixed(ann, "xor_fixed.net");
	fann_save_train_to_fixed(data, "xor_fixed.data", decimal_point);
	
	printf("Cleaning up.\n");
	fann_destroy_train(data);
	fann_destroy(ann);
	
	return 0;
}

	</PRE
></DIV
></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="x184.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="x203.html"
ACCESSKEY="N"
>Next</A
></TD
></TR
><TR
><TD
WIDTH="33%"
ALIGN="left"
VALIGN="top"
>Adjusting Parameters During Training</TD
><TD
WIDTH="34%"
ALIGN="center"
VALIGN="top"
>&nbsp;</TD
><TD
WIDTH="33%"
ALIGN="right"
VALIGN="top"
>Running a Fixed Point ANN</TD
></TR
></TABLE
></DIV
></BODY
></HTML
>

By viewing downloads associated with this article you agree to the Terms of use 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 has no explicit license attached to it but may contain usage terms in the article text or the download files themselves. If in doubt please contact the author via the discussion board below.

A list of licenses authors might use can be found here

About the Author

Software Developer's Journal

Publisher

Poland

Member

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

Neural networks are typically associated with highly specialised applications, developed only by select groups of experst. This misconception has had a highly negative effect on its popularity. Hopefully, the FANN library will help fill this gap.

Type	Article
Licence
First Posted	16 Feb 2006
Views	96,455
Bookmarked	149 times

VC6VC7.1VS.NET2003C
Windows.NETMFCDev, +

		9,877,550 members (31,651 online) Visit CodeProject.TV Discuss CodeProject.TV Sign in Email Password Forgot your password? Sign in using