<!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>Creates a standard backpropagation neural network, which is not fully connected</title>
</head>
<body><div class="manualnavbar" style="text-align: center;">
<div class="prev" style="text-align: left; float: left;"><a href="function.fann-create-sparse-array.html">fann_create_sparse_array</a></div>
<div class="next" style="text-align: right; float: right;"><a href="function.fann-create-standard-array.html">fann_create_standard_array</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-create-sparse" class="refentry">
<div class="refnamediv">
<h1 class="refname">fann_create_sparse</h1>
<p class="verinfo">(PECL fann >= 1.0.0)</p><p class="refpurpose"><span class="refname">fann_create_sparse</span> — <span class="dc-title">Creates a standard backpropagation neural network, which is not fully connected</span></p>
</div>
<div class="refsect1 description" id="refsect1-function.fann-create-sparse-description">
<h3 class="title">Description</h3>
<div class="methodsynopsis dc-description">
<span class="type"><span class="type ReturnType">ReturnType</span></span> <span class="methodname"><strong>fann_create_sparse</strong></span>
( <span class="methodparam"><span class="type">float</span> <code class="parameter">$connection_rate</code></span>
, <span class="methodparam"><span class="type">int</span> <code class="parameter">$num_layers</code></span>
, <span class="methodparam"><span class="type">int</span> <code class="parameter">$num_neurons1</code></span>
, <span class="methodparam"><span class="type">int</span> <code class="parameter">$num_neurons2</code></span>
[, <span class="methodparam"><span class="type">int</span> <code class="parameter">$...</code></span>
] )</div>
<p class="para rdfs-comment">
Creates a standard backpropagation neural network, which is not fully connected.
</p>
</div>
<div class="refsect1 parameters" id="refsect1-function.fann-create-sparse-parameters">
<h3 class="title">Parameters</h3>
<dl>
<dt>
<span class="term"><em><code class="parameter">connection_rate</code></em></span>
<dd>
<p class="para">
The connection rate controls how many connections there will be in the network. If the connection rate
is set to 1, the network will be fully connected, but if it is set to 0.5 only half of the connections
will be set. A connection rate of 1 will yield the same result as <span class="function"><a href="function.fann-create-standard.html" class="function">fann_create_standard()</a></span>.
</p>
</dd>
</dt>
<dt>
<span class="term"><em><code class="parameter">num_layers</code></em></span>
<dd>
<p class="para">
The total number of layers including the input and the output layer.
</p>
</dd>
</dt>
<dt>
<span class="term"><em><code class="parameter">num_neurons1</code></em></span>
<dd>
<p class="para">
Number of neurons in the first layer.
</p>
</dd>
</dt>
<dt>
<span class="term"><em><code class="parameter">num_neurons2</code></em></span>
<dd>
<p class="para">
Number of neurons in the second layer.
</p>
</dd>
</dt>
<dt>
<span class="term"><em><code class="parameter">...</code></em></span>
<dd>
<p class="para">
Number of neurons in other layers.
</p>
</dd>
</dt>
</dl>
</div>
<div class="refsect1 returnvalues" id="refsect1-function.fann-create-sparse-returnvalues">
<h3 class="title">Return Values</h3>
<p class="para">
Returns a neural network resource on success, or <strong><code>FALSE</code></strong> on error.
</p>
</div>
<div class="refsect1 seealso" id="refsect1-function.fann-create-sparse-seealso">
<h3 class="title">See Also</h3>
<p class="para">
<ul class="simplelist">
<li class="member"> <span class="function"><a href="function.fann-create-sparse-array.html" class="function" rel="rdfs-seeAlso">fann_create_sparse_array()</a> - Creates a standard backpropagation neural network, which is not fully connected using an array of layer sizes</span></li>
<li class="member"> <span class="function"><a href="function.fann-create-standard.html" class="function" rel="rdfs-seeAlso">fann_create_standard()</a> - Creates a standard fully connected backpropagation neural network</span></li>
<li class="member"> <span class="function"><a href="function.fann-create-shortcut.html" class="function" rel="rdfs-seeAlso">fann_create_shortcut()</a> - Creates a standard backpropagation neural network which is not fully connectected and has shortcut connections</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-create-sparse-array.html">fann_create_sparse_array</a></div>
<div class="next" style="text-align: right; float: right;"><a href="function.fann-create-standard-array.html">fann_create_standard_array</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>
