<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd"> <html> <head> <meta http-equiv="content-type" content="text/html; charset=UTF-8"> <title>Initialize the weights using Widrow + Nguyen’s algorithm</title> </head> <body><div class="manualnavbar" style="text-align: center;"> <div class="prev" style="text-align: left; float: left;"><a href="function.fann-get-training-algorithm.html">fann_get_training_algorithm</a></div> <div class="next" style="text-align: right; float: right;"><a href="function.fann-length-train-data.html">fann_length_train_data</a></div> <div class="up"><a href="ref.fann.html">Fann Functions</a></div> <div class="home"><a href="index.html">PHP Manual</a></div> </div><hr /><div id="function.fann-init-weights" class="refentry"> <div class="refnamediv"> <h1 class="refname">fann_init_weights</h1> <p class="verinfo">(PECL fann >= 1.0.0)</p><p class="refpurpose"><span class="refname">fann_init_weights</span> — <span class="dc-title">Initialize the weights using Widrow + Nguyen’s algorithm</span></p> </div> <div class="refsect1 description" id="refsect1-function.fann-init-weights-description"> <h3 class="title">Description</h3> <div class="methodsynopsis dc-description"> <span class="type">bool</span> <span class="methodname"><strong>fann_init_weights</strong></span> ( <span class="methodparam"><span class="type">resource</span> <code class="parameter">$ann</code></span> , <span class="methodparam"><span class="type">resource</span> <code class="parameter">$train_data</code></span> )</div> <p class="para rdfs-comment"> Initialize the weights using Widrow + Nguyen’s algorithm. </p> <p class="para"> This function behaves similarly to <span class="function"><a href="function.fann-randomize-weights.html" class="function">fann_randomize_weights()</a></span>. It will use the algorithm developed by Derrick Nguyen and Bernard Widrow 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 less efficient than a purely random initialization. </p> <p class="para"> The algorithm requires access to the range of the input data (for example largest and smallest input), and therefore accepts a second argument, data, which is the training data that will be used to train the network. </p> </div> <div class="refsect1 parameters" id="refsect1-function.fann-init-weights-parameters"> <h3 class="title">Parameters</h3> <dl> <dt> <span class="term"><em><code class="parameter">ann</code></em></span> <dd> <p class="para">Neural network <span class="type"><a href="language.types.resource.html" class="type resource">resource</a></span>.</p> </dd> </dt> <dt> <span class="term"><em><code class="parameter">train_data</code></em></span> <dd> <p class="para">Neural network training data <span class="type"><a href="language.types.resource.html" class="type resource">resource</a></span>.</p> </dd> </dt> </dl> </div> <div class="refsect1 returnvalues" id="refsect1-function.fann-init-weights-returnvalues"> <h3 class="title">Return Values</h3> <p class="para">Returns <strong><code>TRUE</code></strong> on success, or <strong><code>FALSE</code></strong> otherwise.</p> </div> <div class="refsect1 seealso" id="refsect1-function.fann-init-weights-seealso"> <h3 class="title">See Also</h3> <p class="para"> <ul class="simplelist"> <li class="member"> <span class="function"><a href="function.fann-randomize-weights.html" class="function" rel="rdfs-seeAlso">fann_randomize_weights()</a> - Give each connection a random weight between min_weight and max_weight</span></li> <li class="member"> <span class="function"><a href="function.fann-read-train-from-file.html" class="function" rel="rdfs-seeAlso">fann_read_train_from_file()</a> - Reads a file that stores training data</span></li> </ul> </p> </div> </div><hr /><div class="manualnavbar" style="text-align: center;"> <div class="prev" style="text-align: left; float: left;"><a href="function.fann-get-training-algorithm.html">fann_get_training_algorithm</a></div> <div class="next" style="text-align: right; float: right;"><a href="function.fann-length-train-data.html">fann_length_train_data</a></div> <div class="up"><a href="ref.fann.html">Fann Functions</a></div> <div class="home"><a href="index.html">PHP Manual</a></div> </div></body></html>