mirror of
https://github.com/fofolee/uTools-Manuals.git
synced 2025-06-17 21:16:57 +08:00
120 lines
4.7 KiB
HTML
120 lines
4.7 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>为已应用的神经元和层设置激活函数</title>
|
||
</head>
|
||
<body class="docs"><div id="layout">
|
||
<div id="layout-content"><div id="function.fann-set-activation-function" class="refentry">
|
||
<div class="refnamediv">
|
||
<h1 class="refname">fann_set_activation_function</h1>
|
||
<p class="verinfo">(PECL fann >= 1.0.0)</p><p class="refpurpose"><span class="refname">fann_set_activation_function</span> — <span class="dc-title">为已应用的神经元和层设置激活函数</span></p>
|
||
|
||
</div>
|
||
|
||
<div class="refsect1 description" id="refsect1-function.fann-set-activation-function-description">
|
||
<h3 class="title">说明</h3>
|
||
<div class="methodsynopsis dc-description">
|
||
<span class="methodname"><strong>fann_set_activation_function</strong></span>
|
||
( <span class="methodparam"><span class="type">resource</span> <code class="parameter">$ann</code></span>
|
||
, <span class="methodparam"><span class="type">int</span> <code class="parameter">$activation_function</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">bool</span></div>
|
||
|
||
<p class="para rdfs-comment">
|
||
为层数为 <em>layer</em>，神经经元数为 <em>neuron</em> 的神经元设置激活函数，将输入层记为0.
|
||
</p>
|
||
<p class="para">
|
||
在输出层中的神经元设置激活函数是不可能的。
|
||
</p>
|
||
<p class="para">
|
||
在选择激活函数时，注意激活函数有不同的范围，这个很重要哦。
|
||
<strong><code>FANN_SIGMOID</code></strong> 就是个例子。它的范围是0 -1，然而 <strong><code>FANN_SIGMOID_SYMMETRIC</code></strong> 的范围是-1 - 1， <strong><code>FANN_LINEAR</code></strong> 却是无限的。
|
||
</p>
|
||
<p class="para">
|
||
应用的激活函数应该是<a href="fann.constants.html#constants.fann-activation-funcs" class="link">激活函数</a>常量之一。
|
||
</p>
|
||
<p class="para">
|
||
返回值是<a href="fann.constants.html#constants.fann-train" class="link">激活函数</a>常量之一。
|
||
</p>
|
||
</div>
|
||
|
||
|
||
<div class="refsect1 parameters" id="refsect1-function.fann-set-activation-function-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">activation_function</code></dt>
|
||
|
||
<dd>
|
||
|
||
<p class="para">
|
||
<a href="fann.constants.html#constants.fann-activation-funcs" class="link">激活函数</a>常量。
|
||
</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-set-activation-function-returnvalues">
|
||
<h3 class="title">返回值</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-set-activation-function-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_layer.html" class="function" rel="rdfs-seeAlso">fann_set_activation_function_layer()</a> - 为已应用的层中所有的神经元设置激活函数。</span></li>
|
||
<li class="member"><span class="function"><a href="fann_set_activation_function_hidden.html" class="function" rel="rdfs-seeAlso">fann_set_activation_function_hidden()</a> - 为所有隐藏层设置激活函数</span></li>
|
||
<li class="member"><span class="function"><a href="fann_set_activation_function_output.html" class="function" rel="rdfs-seeAlso">fann_set_activation_function_output()</a> - 为输出层设置激活函数</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>
|
||
<li class="member"><span class="function"><a href="fann_get_activation_function.html" class="function" rel="rdfs-seeAlso">fann_get_activation_function()</a> - 返回激励函数</span></li>
|
||
</ul>
|
||
</p>
|
||
</div>
|
||
|
||
|
||
|
||
</div></div></div></body></html> |