mirror of
https://github.com/fofolee/uTools-Manuals.git
synced 2025-06-18 13:57:03 +08:00
109 lines
4.2 KiB
HTML
109 lines
4.2 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>为提供的神经和网络层数返回激活陡度</title>
|
||
</head>
|
||
<body class="docs"><div id="layout">
|
||
<div id="layout-content"><div id="function.fann-get-activation-steepness" class="refentry">
|
||
<div class="refnamediv">
|
||
<h1 class="refname">fann_get_activation_steepness</h1>
|
||
<p class="verinfo">(PECL fann >= 1.0.0)</p><p class="refpurpose"><span class="refname">fann_get_activation_steepness</span> — <span class="dc-title">为提供的神经和网络层数返回激活陡度</span></p>
|
||
|
||
</div>
|
||
|
||
<div class="refsect1 description" id="refsect1-function.fann-get-activation-steepness-description">
|
||
<h3 class="title">说明</h3>
|
||
<div class="methodsynopsis dc-description">
|
||
<span class="methodname"><strong>fann_get_activation_steepness</strong></span>
|
||
( <span class="methodparam"><span class="type">resource</span> <code class="parameter">$ann</code></span>
|
||
, <span class="methodparam"><span class="type">int</span> <code class="parameter">$layer</code></span>
|
||
, <span class="methodparam"><span class="type">int</span> <code class="parameter">$neuron</code></span>
|
||
) : <span class="type">float</span></div>
|
||
|
||
<p class="para rdfs-comment">
|
||
获取神经元数为 <em>neuron</em> 层数为
|
||
<em>layer</em>神经网络的激活陡度，将输入层数计为1层。
|
||
</p>
|
||
<p class="para">
|
||
在输入层中是不可能获取激活陡度。
|
||
</p>
|
||
<p class="para">
|
||
激活函数的陡度表明了激活函数从最小到最大有多块。一个高值表明将会提供一个更高效的训练。
|
||
</p>
|
||
<p class="para">
|
||
在训练神经网络时，输出值应该处于极端(通常是 0 和 1，取决于激励函数)，一般陡峭的激活函数将会被使用(比如为1.0时)。
|
||
</p>
|
||
<p class="para">
|
||
默认的激活陡度是0.5.
|
||
</p>
|
||
</div>
|
||
|
||
|
||
<div class="refsect1 parameters" id="refsect1-function.fann-get-activation-steepness-parameters">
|
||
<h3 class="title">参数</h3>
|
||
<dl>
|
||
|
||
|
||
<dt>
|
||
<code class="parameter">ann</code></dt>
|
||
|
||
<dd>
|
||
|
||
<p class="para">Neural network <span class="type"><a href="language.types.resource.html" class="type resource">resource</a></span>.</p>
|
||
</dd>
|
||
|
||
|
||
|
||
<dt>
|
||
<code class="parameter">layer</code></dt>
|
||
|
||
<dd>
|
||
|
||
<p class="para">
|
||
层数
|
||
</p>
|
||
</dd>
|
||
|
||
|
||
|
||
<dt>
|
||
<code class="parameter">neuron</code></dt>
|
||
|
||
<dd>
|
||
|
||
<p class="para">
|
||
神经元数
|
||
</p>
|
||
</dd>
|
||
|
||
|
||
</dl>
|
||
|
||
</div>
|
||
|
||
|
||
<div class="refsect1 returnvalues" id="refsect1-function.fann-get-activation-steepness-returnvalues">
|
||
<h3 class="title">返回值</h3>
|
||
<p class="para">
|
||
激活陡度，当神经元在神经网络中没定义时为-1，错误时返回 <strong><code>FALSE</code></strong> .
|
||
</p>
|
||
</div>
|
||
|
||
|
||
<div class="refsect1 seealso" id="refsect1-function.fann-get-activation-steepness-seealso">
|
||
<h3 class="title">参见</h3>
|
||
<p class="para">
|
||
<ul class="simplelist">
|
||
<li class="member"><span class="function"><a href="fann_set_activation_function.html" class="function" rel="rdfs-seeAlso">fann_set_activation_function()</a> - 为已应用的神经元和层设置激活函数</span></li>
|
||
<li class="member"><span class="function"><a href="fann_set_activation_steepness_layer.html" class="function" rel="rdfs-seeAlso">fann_set_activation_steepness_layer()</a> - 为提供的层中所有的神经元设置激活陡度</span></li>
|
||
<li class="member"><span class="function"><a href="fann_set_activation_steepness_hidden.html" class="function" rel="rdfs-seeAlso">fann_set_activation_steepness_hidden()</a> - 为所有隐藏层中所有的神经元设置激活函数陡度</span></li>
|
||
<li class="member"><span class="function"><a href="fann_set_activation_steepness_output.html" class="function" rel="rdfs-seeAlso">fann_set_activation_steepness_output()</a> - 在输出层中设置激活陡度</span></li>
|
||
<li class="member"><span class="function"><a href="fann_set_activation_steepness.html" class="function" rel="rdfs-seeAlso">fann_set_activation_steepness()</a> - 为提供的神经元和层设置激活陡度</span></li>
|
||
</ul>
|
||
</p>
|
||
</div>
|
||
|
||
|
||
|
||
</div></div></div></body></html> |