mirror of
https://github.com/fofolee/uTools-Manuals.git
synced 2025-06-18 05:26:57 +08:00
88 lines
3.5 KiB
HTML
88 lines
3.5 KiB
HTML
<!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>创建一个全连接的反向传播神经网络，该网络使用一个表示每层大小的数组来构造。</title>
|
||
</head>
|
||
<body class="docs"><div id="layout">
|
||
<div id="layout-content"><div id="function.fann-create-standard-array" class="refentry">
|
||
<div class="refnamediv">
|
||
<h1 class="refname">fann_create_standard_array</h1>
|
||
<p class="verinfo">(PECL fann >= 1.0.0)</p><p class="refpurpose"><span class="refname">fann_create_standard_array</span> — <span class="dc-title">创建一个全连接的反向传播神经网络，该网络使用一个表示每层大小的数组来构造。</span></p>
|
||
|
||
</div>
|
||
|
||
<div class="refsect1 description" id="refsect1-function.fann-create-standard-array-description">
|
||
<h3 class="title">说明</h3>
|
||
<div class="methodsynopsis dc-description">
|
||
<span class="methodname"><strong>fann_create_standard_array</strong></span>
|
||
( <span class="methodparam"><span class="type">int</span> <code class="parameter">$num_layers</code></span>
|
||
, <span class="methodparam"><span class="type">array</span> <code class="parameter">$layers</code></span>
|
||
) : <span class="type">resource</span></div>
|
||
|
||
<p class="para rdfs-comment">
|
||
创建一个标准的全连接反向传播神经网络。
|
||
</p>
|
||
<p class="para">
|
||
每一层都将会有一个偏置神经元 (除了输出层),该偏置神经元将会连接下一层所有的神经元。当运行网络时，偏置神经节点一直发出1信号。
|
||
</p>
|
||
<p class="para">
|
||
请使用 <span class="function"><a href="fann_destroy.html" class="function">fann_destroy()</a></span> 函数来销毁神经网络。
|
||
</p>
|
||
</div>
|
||
|
||
|
||
<div class="refsect1 parameters" id="refsect1-function.fann-create-standard-array-parameters">
|
||
<h3 class="title">参数</h3>
|
||
<dl>
|
||
|
||
|
||
<dt>
|
||
<code class="parameter">num_layers</code></dt>
|
||
|
||
<dd>
|
||
|
||
<p class="para">
|
||
神经网络层数，包括输入输出层。
|
||
</p>
|
||
</dd>
|
||
|
||
|
||
|
||
<dt>
|
||
<code class="parameter">layers</code></dt>
|
||
|
||
<dd>
|
||
|
||
<p class="para">
|
||
表示每层大小的数组。
|
||
</p>
|
||
</dd>
|
||
|
||
|
||
</dl>
|
||
|
||
</div>
|
||
|
||
|
||
<div class="refsect1 returnvalues" id="refsect1-function.fann-create-standard-array-returnvalues">
|
||
<h3 class="title">返回值</h3>
|
||
<p class="para">
|
||
成功则返回神经网络，错误则返回 <strong><code>FALSE</code></strong> .
|
||
</p>
|
||
</div>
|
||
|
||
|
||
<div class="refsect1 seealso" id="refsect1-function.fann-create-standard-array-seealso">
|
||
<h3 class="title">参见</h3>
|
||
<p class="para">
|
||
<ul class="simplelist">
|
||
<li class="member"><span class="function"><a href="fann_create_standard.html" class="function" rel="rdfs-seeAlso">fann_create_standard()</a> - 创建标准的全连接反向传播神经网络。</span></li>
|
||
<li class="member"><span class="function"><a href="fann_create_sparse.html" class="function" rel="rdfs-seeAlso">fann_create_sparse()</a> - 创建一个标准的反向传播神经网络，该网络不是全连接。</span></li>
|
||
<li class="member"><span class="function"><a href="fann_create_shortcut.html" class="function" rel="rdfs-seeAlso">fann_create_shortcut()</a> - 创建一个含快捷连接而非全连接的标准反向传播神经网络。</span></li>
|
||
</ul>
|
||
</p>
|
||
</div>
|
||
|
||
|
||
</div></div></div></body></html> |