|
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<HTML
><HEAD
><TITLE
>Precision of a Fixed Point ANN</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="Fixed Point Usage"
HREF="c189.html"><LINK
REL="PREVIOUS"
TITLE="Running a Fixed Point ANN"
HREF="x203.html"><LINK
REL="NEXT"
TITLE="Neural Network Theory"
HREF="c225.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="x203.html"
ACCESSKEY="P"
>Prev</A
></TD
><TD
WIDTH="80%"
ALIGN="center"
VALIGN="bottom"
>Chapter 3. Fixed Point Usage</TD
><TD
WIDTH="10%"
ALIGN="right"
VALIGN="bottom"
><A
HREF="c225.html"
ACCESSKEY="N"
>Next</A
></TD
></TR
></TABLE
><HR
ALIGN="LEFT"
WIDTH="100%"></DIV
><DIV
CLASS="section"
><H1
CLASS="section"
><A
NAME="fixed.precision"
>3.3. Precision of a Fixed Point ANN</A
></H1
><P
> The fixed point ANN is not as precise as a floating point ANN, furthermore it approximates the sigmoid function by a stepwise linear function. Therefore,
it is always a good idea to test the fixed point ANN after loading it from a file. This can be done by calculating the mean square error as described
<A
HREF="x161.html#example.calc_mse"
>earlier</A
>. There is, however, one problem with this approach: The training data stored in the file is in floating
point format. Therefore, it is possible to save this data in a fixed point format from within the floating point program. This is done by the function
<A
HREF="r648.html"
><CODE
CLASS="function"
>fann_save_train_to_fixed</CODE
></A
>. Please note that this function takes the decimal point
as an argument, meaning that the decimal point should be calculated first by using the
<A
HREF="r494.html"
><CODE
CLASS="function"
>fann_save_to_fixed</CODE
></A
> function.
</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="x203.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="c225.html"
ACCESSKEY="N"
>Next</A
></TD
></TR
><TR
><TD
WIDTH="33%"
ALIGN="left"
VALIGN="top"
>Running a Fixed Point ANN</TD
><TD
WIDTH="34%"
ALIGN="center"
VALIGN="top"
><A
HREF="c189.html"
ACCESSKEY="U"
>Up</A
></TD
><TD
WIDTH="33%"
ALIGN="right"
VALIGN="top"
>Neural Network Theory</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.