r421.html
来自「一个功能强大的神经网络分析程序」· HTML 代码 · 共 228 行
HTML
228 行
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN""http://www.w3.org/TR/html4/loose.dtd"><HTML><HEAD><TITLE>fann_init_weights</TITLE><link href="../style.css" rel="stylesheet" type="text/css"><METANAME="GENERATOR"CONTENT="Modular DocBook HTML Stylesheet Version 1.79"><LINKREL="HOME"TITLE="Fast Artificial Neural Network Library"HREF="index.html"><LINKREL="UP"TITLE="Creation, Destruction, and Execution"HREF="c253.html#api.sec.create_destroy"><LINKREL="PREVIOUS"TITLE="fann_randomize_weights"HREF="r396.html"><LINKREL="NEXT"TITLE="fann_print_connections"HREF="r448.html"></HEAD><BODYCLASS="refentry"BGCOLOR="#FFFFFF"TEXT="#000000"LINK="#0000FF"VLINK="#840084"ALINK="#0000FF"><DIVCLASS="NAVHEADER"><TABLESUMMARY="Header navigation table"WIDTH="100%"BORDER="0"CELLPADDING="0"CELLSPACING="0"><TR><THCOLSPAN="3"ALIGN="center">Fast Artificial Neural Network Library</TH></TR><TR><TDWIDTH="10%"ALIGN="left"VALIGN="bottom"><AHREF="r396.html"ACCESSKEY="P">Prev</A></TD><TDWIDTH="80%"ALIGN="center"VALIGN="bottom"></TD><TDWIDTH="10%"ALIGN="right"VALIGN="bottom"><AHREF="r448.html"ACCESSKEY="N">Next</A></TD></TR></TABLE><HRALIGN="LEFT"WIDTH="100%"></DIV><H1><ANAME="api.fann_init_weights"></A>fann_init_weights</H1><DIVCLASS="refnamediv"><ANAME="AEN422"></A><H2>Name</H2>fann_init_weights -- Initialize the weight of each connection.</DIV><DIVCLASS="refsect1"><ANAME="AEN425"></A><H2>Description</H2><codeclass="methodsynopsis"> <spanclass="type">void </span>fann_init_weights(<spanclass="methodparam"><spanclass="type">struct fann * </span><spanclass="parameter">ann</span></span><spanclass="methodparam">, <spanclass="type">struct fann_train_data * </span><spanclass="parameter">train_data</span></span>); </code><P> This function behaves similarly to <AHREF="r396.html"><CODECLASS="function">fann_randomize_weights</CODE></A>. It will use the algorithm developed by Derrick Nguyen and Bernard Widrow [<AHREF="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 <SPANCLASS="emphasis"><ICLASS="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, <CODECLASS="parameter">data</CODE>, which is the training data that will be used to train the network. </P><P> See also: <AHREF="c104.html#adv.adj"><I>Adjusting Parameters</I></A>, <AHREF="r396.html"><CODECLASS="function">fann_randomize_weights</CODE></A> </P><P>This function appears in FANN >= 1.1.0.</P></DIV><DIVCLASS="NAVFOOTER"><HRALIGN="LEFT"WIDTH="100%"><TABLESUMMARY="Footer navigation table"WIDTH="100%"BORDER="0"CELLPADDING="0"CELLSPACING="0"><TR><TDWIDTH="33%"ALIGN="left"VALIGN="top"><AHREF="r396.html"ACCESSKEY="P">Prev</A></TD><TDWIDTH="34%"ALIGN="center"VALIGN="top"><AHREF="index.html"ACCESSKEY="H">Home</A></TD><TDWIDTH="33%"ALIGN="right"VALIGN="top"><AHREF="r448.html"ACCESSKEY="N">Next</A></TD></TR><TR><TDWIDTH="33%"ALIGN="left"VALIGN="top">fann_randomize_weights</TD><TDWIDTH="34%"ALIGN="center"VALIGN="top"><AHREF="c253.html#api.sec.create_destroy"ACCESSKEY="U">Up</A></TD><TDWIDTH="33%"ALIGN="right"VALIGN="top">fann_print_connections</TD></TR></TABLE></DIV></BODY></HTML>⌨️ 快捷键说明
复制代码Ctrl + C
搜索代码Ctrl + F
全屏模式F11
增大字号Ctrl + =
减小字号Ctrl + -
显示快捷键?