|
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<HTML
><HEAD
><TITLE
>fann_init_weights</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="Creation, Destruction, and Execution"
HREF="c253.html#api.sec.create_destroy"><LINK
REL="PREVIOUS"
TITLE="fann_randomize_weights"
HREF="r396.html"><LINK
REL="NEXT"
TITLE="fann_print_connections"
HREF="r448.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="r396.html"
ACCESSKEY="P"
>Prev</A
></TD
><TD
WIDTH="80%"
ALIGN="center"
VALIGN="bottom"
></TD
><TD
WIDTH="10%"
ALIGN="right"
VALIGN="bottom"
><A
HREF="r448.html"
ACCESSKEY="N"
>Next</A
></TD
></TR
></TABLE
><HR
ALIGN="LEFT"
WIDTH="100%"></DIV
><H1
><A
NAME="api.fann_init_weights"
></A
>fann_init_weights</H1
><DIV
CLASS="refnamediv"
><A
NAME="AEN422"
></A
><H2
>Name</H2
>fann_init_weights -- Initialize the weight of each connection.</DIV
><DIV
CLASS="refsect1"
><A
NAME="AEN425"
></A
><H2
>Description</H2
><code
class="methodsynopsis"
> <span
class="type"
>void </span
>fann_init_weights(<span
class="methodparam"
><span
class="type"
>struct fann * </span
><span
class="parameter"
>ann</span
></span
><span
class="methodparam"
>, <span
class="type"
>struct fann_train_data * </span
><span
class="parameter"
>train_data</span
></span
>); </code
><P
> This function behaves similarly to <A
HREF="r396.html"
><CODE
CLASS="function"
>fann_randomize_weights</CODE
></A
>.
It will use the algorithm developed by Derrick Nguyen and Bernard Widrow
[<A
HREF="b3048.html#bib.nguyen_1990"
><I
>Nguyen and Widrow, 1990</I
></A
>] to set the weights in such a way as to speed up training.
This technique is not always successful, and in some cases can be <SPAN
CLASS="emphasis"
><I
CLASS="emphasis"
>less</I
></SPAN
> efficient than a purely random
initialization.
</P
><P
> The algorithm requires access to the range of the input data (ie, largest and smallest input), and therefore accepts a second
argument, <VAR
CLASS="parameter"
>data</VAR
>, which is the training data that will be used to train the network.
</P
><P
> See also: <A
HREF="c104.html#adv.adj"
><I
>Adjusting Parameters</I
></A
>,
<A
HREF="r396.html"
><CODE
CLASS="function"
>fann_randomize_weights</CODE
></A
>
</P
><P
>This function appears in FANN >= 1.1.0.</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="r396.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="r448.html"
ACCESSKEY="N"
>Next</A
></TD
></TR
><TR
><TD
WIDTH="33%"
ALIGN="left"
VALIGN="top"
>fann_randomize_weights</TD
><TD
WIDTH="34%"
ALIGN="center"
VALIGN="top"
><A
HREF="c253.html#api.sec.create_destroy"
ACCESSKEY="U"
>Up</A
></TD
><TD
WIDTH="33%"
ALIGN="right"
VALIGN="top"
>fann_print_connections</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.