<?xml version="1.0"?>
<feed xmlns="http://www.w3.org/2005/Atom" xml:lang="en">
	<id>https://marovi.ai/index.php?action=history&amp;feed=atom&amp;title=Translations%3ANeural_Networks%2F28%2Fzh</id>
	<title>Translations:Neural Networks/28/zh - Revision history</title>
	<link rel="self" type="application/atom+xml" href="https://marovi.ai/index.php?action=history&amp;feed=atom&amp;title=Translations%3ANeural_Networks%2F28%2Fzh"/>
	<link rel="alternate" type="text/html" href="https://marovi.ai/index.php?title=Translations:Neural_Networks/28/zh&amp;action=history"/>
	<updated>2026-04-28T03:30:14Z</updated>
	<subtitle>Revision history for this page on the wiki</subtitle>
	<generator>MediaWiki 1.39.1</generator>
	<entry>
		<id>https://marovi.ai/index.php?title=Translations:Neural_Networks/28/zh&amp;diff=17923&amp;oldid=prev</id>
		<title>DeployBot: Batch translate Neural Networks unit 28 → zh</title>
		<link rel="alternate" type="text/html" href="https://marovi.ai/index.php?title=Translations:Neural_Networks/28/zh&amp;diff=17923&amp;oldid=prev"/>
		<updated>2026-04-27T23:41:03Z</updated>

		<summary type="html">&lt;p&gt;Batch translate Neural Networks unit 28 → zh&lt;/p&gt;
&lt;table style=&quot;background-color: #fff; color: #202122;&quot; data-mw=&quot;interface&quot;&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;tr class=&quot;diff-title&quot; lang=&quot;en&quot;&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;← Older revision&lt;/td&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;Revision as of 23:41, 27 April 2026&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l1&quot;&gt;Line 1:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Line 1:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;[[Convolutional Neural Networks]]&amp;#039;&amp;#039;&amp;#039;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（CNN）— 为图像等网格结构数据设计，使用局部连接和权重共享。&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;[[Convolutional Neural Networks]]&amp;#039;&amp;#039;&amp;#039;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（CNN）—— 为图像等网格结构数据而设计，使用局部连接和权重共享。&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;[[Recurrent Neural Networks]]&amp;#039;&amp;#039;&amp;#039;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（RNN）— 为序列数据设计，连接形成循环以维持隐藏状态。&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;[[Recurrent Neural Networks]]&amp;#039;&amp;#039;&amp;#039;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（RNN）—— 为序列数据而设计，连接形成循环以保持隐藏状态。&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Transformers&lt;/del&gt;&amp;#039;&amp;#039;&amp;#039; &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;— 基于注意力的架构，已在自然语言处理领域占据主导地位，并在视觉领域日益普及。&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;{{Term|transformer|Transformer}}&lt;/ins&gt;&amp;#039;&amp;#039;&amp;#039; &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;—— 基于{{Term|attention|注意力}}的架构，已在自然语言处理领域占据主导地位，并日益在视觉领域得到应用。&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Autoencoders&lt;/del&gt;&amp;#039;&amp;#039;&amp;#039; &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;— 训练用于重建其输入的网络，用于降维和生成建模。&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;自编码器&lt;/ins&gt;&amp;#039;&amp;#039;&amp;#039; &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;—— 训练用于重建其输入的网络，用于降维和生成式建模。&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;生成对抗网络&amp;#039;&amp;#039;&amp;#039;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（GAN）— 成对的网络（生成器和判别器）在竞争中进行训练，以生成逼真的数据。&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;生成对抗网络&amp;#039;&amp;#039;&amp;#039;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（GAN）—— 成对的网络（生成器和判别器）通过竞争训练，以生成逼真的数据。&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;

&lt;!-- diff cache key mediawiki:diff::1.12:old-14865:rev-17923 --&gt;
&lt;/table&gt;</summary>
		<author><name>DeployBot</name></author>
	</entry>
	<entry>
		<id>https://marovi.ai/index.php?title=Translations:Neural_Networks/28/zh&amp;diff=14865&amp;oldid=prev</id>
		<title>DeployBot: Batch translate Neural Networks unit 28 → zh</title>
		<link rel="alternate" type="text/html" href="https://marovi.ai/index.php?title=Translations:Neural_Networks/28/zh&amp;diff=14865&amp;oldid=prev"/>
		<updated>2026-04-27T22:03:00Z</updated>

		<summary type="html">&lt;p&gt;Batch translate Neural Networks unit 28 → zh&lt;/p&gt;
&lt;table style=&quot;background-color: #fff; color: #202122;&quot; data-mw=&quot;interface&quot;&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;tr class=&quot;diff-title&quot; lang=&quot;en&quot;&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;← Older revision&lt;/td&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;Revision as of 22:03, 27 April 2026&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l1&quot;&gt;Line 1:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Line 1:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;[[Convolutional Neural Networks]]&amp;#039;&amp;#039;&amp;#039;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（CNN）——专为图像等网格结构数据设计，使用局部连接和权重共享。&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;[[Convolutional Neural Networks]]&amp;#039;&amp;#039;&amp;#039;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（CNN）— 为图像等网格结构数据设计，使用局部连接和权重共享。&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;[[Recurrent Neural Networks]]&amp;#039;&amp;#039;&amp;#039;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（RNN）——专为序列数据设计，连接形成环路以维持隐藏状态。&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;[[Recurrent Neural Networks]]&amp;#039;&amp;#039;&amp;#039;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（RNN）— 为序列数据设计，连接形成循环以维持隐藏状态。&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;Transformers&amp;#039;&amp;#039;&amp;#039;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;——基于 attention 的架构，已在自然语言处理中占主导地位，并越来越多地用于视觉领域。&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;Transformers&amp;#039;&amp;#039;&amp;#039; &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;— 基于注意力的架构，已在自然语言处理领域占据主导地位，并在视觉领域日益普及。&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;Autoencoders&amp;#039;&amp;#039;&amp;#039;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;——经过训练来重建其输入的网络，用于降维和生成建模。&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;Autoencoders&amp;#039;&amp;#039;&amp;#039; &lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;— 训练用于重建其输入的网络，用于降维和生成建模。&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;生成对抗网络&amp;#039;&amp;#039;&amp;#039;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（GAN）——成对的网络（生成器和判别器）以竞争方式训练以生成逼真的数据。&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;生成对抗网络&amp;#039;&amp;#039;&amp;#039;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（GAN）— 成对的网络（生成器和判别器）在竞争中进行训练，以生成逼真的数据。&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;/table&gt;</summary>
		<author><name>DeployBot</name></author>
	</entry>
	<entry>
		<id>https://marovi.ai/index.php?title=Translations:Neural_Networks/28/zh&amp;diff=5341&amp;oldid=prev</id>
		<title>DeployBot: Batch translate Neural Networks unit 28 → zh</title>
		<link rel="alternate" type="text/html" href="https://marovi.ai/index.php?title=Translations:Neural_Networks/28/zh&amp;diff=5341&amp;oldid=prev"/>
		<updated>2026-04-27T03:35:03Z</updated>

		<summary type="html">&lt;p&gt;Batch translate Neural Networks unit 28 → zh&lt;/p&gt;
&lt;table style=&quot;background-color: #fff; color: #202122;&quot; data-mw=&quot;interface&quot;&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;col class=&quot;diff-marker&quot; /&gt;
				&lt;col class=&quot;diff-content&quot; /&gt;
				&lt;tr class=&quot;diff-title&quot; lang=&quot;en&quot;&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;← Older revision&lt;/td&gt;
				&lt;td colspan=&quot;2&quot; style=&quot;background-color: #fff; color: #202122; text-align: center;&quot;&gt;Revision as of 03:35, 27 April 2026&lt;/td&gt;
				&lt;/tr&gt;&lt;tr&gt;&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot; id=&quot;mw-diff-left-l1&quot;&gt;Line 1:&lt;/td&gt;
&lt;td colspan=&quot;2&quot; class=&quot;diff-lineno&quot;&gt;Line 1:&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;[[Convolutional Neural Networks&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;|卷积神经网络&lt;/del&gt;]]&amp;#039;&amp;#039;&amp;#039;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（CNN）—— 面向图像等网格结构数据，采用局部连接与权重共享。&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;[[Convolutional Neural Networks]]&amp;#039;&amp;#039;&amp;#039;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（CNN）——专为图像等网格结构数据设计，使用局部连接和权重共享。&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;[[Recurrent Neural Networks&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;|循环神经网络&lt;/del&gt;]]&amp;#039;&amp;#039;&amp;#039;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（RNN）—— 面向序列数据，通过形成回路的连接维持隐藏状态。&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;[[Recurrent Neural Networks]]&amp;#039;&amp;#039;&amp;#039;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（RNN）——专为序列数据设计，连接形成环路以维持隐藏状态。&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Transformer&lt;/del&gt;&amp;#039;&amp;#039;&amp;#039; &lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;—— 基于注意力机制的架构，已在自然语言处理领域占据主导地位，并日益应用于视觉领域。&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Transformers&lt;/ins&gt;&amp;#039;&amp;#039;&amp;#039;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;——基于 attention 的架构，已在自然语言处理中占主导地位，并越来越多地用于视觉领域。&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;自编码器&lt;/del&gt;&amp;#039;&amp;#039;&amp;#039;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（autoencoder）—— 训练目标是重建输入，常用于降维与生成式建模。&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;Autoencoders&lt;/ins&gt;&amp;#039;&amp;#039;&amp;#039;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;——经过训练来重建其输入的网络，用于降维和生成建模。&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;
&lt;tr&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;−&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;生成对抗网络&amp;#039;&amp;#039;&amp;#039;&lt;del style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（GAN）—— 由生成器与判别器两个网络相互对抗训练，用于生成逼真的数据。&lt;/del&gt;&lt;/div&gt;&lt;/td&gt;&lt;td class=&quot;diff-marker&quot; data-marker=&quot;+&quot;&gt;&lt;/td&gt;&lt;td style=&quot;color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;&quot;&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;生成对抗网络&amp;#039;&amp;#039;&amp;#039;&lt;ins style=&quot;font-weight: bold; text-decoration: none;&quot;&gt;（GAN）——成对的网络（生成器和判别器）以竞争方式训练以生成逼真的数据。&lt;/ins&gt;&lt;/div&gt;&lt;/td&gt;&lt;/tr&gt;

&lt;!-- diff cache key mediawiki:diff::1.12:old-2321:rev-5341 --&gt;
&lt;/table&gt;</summary>
		<author><name>DeployBot</name></author>
	</entry>
	<entry>
		<id>https://marovi.ai/index.php?title=Translations:Neural_Networks/28/zh&amp;diff=2321&amp;oldid=prev</id>
		<title>DeployBot: [deploy-bot] Translate Neural Networks unit 28 to zh</title>
		<link rel="alternate" type="text/html" href="https://marovi.ai/index.php?title=Translations:Neural_Networks/28/zh&amp;diff=2321&amp;oldid=prev"/>
		<updated>2026-04-27T00:25:46Z</updated>

		<summary type="html">&lt;p&gt;[deploy-bot] Translate Neural Networks unit 28 to zh&lt;/p&gt;
&lt;p&gt;&lt;b&gt;New page&lt;/b&gt;&lt;/p&gt;&lt;div&gt;* &amp;#039;&amp;#039;&amp;#039;[[Convolutional Neural Networks|卷积神经网络]]&amp;#039;&amp;#039;&amp;#039;（CNN）—— 面向图像等网格结构数据，采用局部连接与权重共享。&lt;br /&gt;
* &amp;#039;&amp;#039;&amp;#039;[[Recurrent Neural Networks|循环神经网络]]&amp;#039;&amp;#039;&amp;#039;（RNN）—— 面向序列数据，通过形成回路的连接维持隐藏状态。&lt;br /&gt;
* &amp;#039;&amp;#039;&amp;#039;Transformer&amp;#039;&amp;#039;&amp;#039; —— 基于注意力机制的架构，已在自然语言处理领域占据主导地位，并日益应用于视觉领域。&lt;br /&gt;
* &amp;#039;&amp;#039;&amp;#039;自编码器&amp;#039;&amp;#039;&amp;#039;（autoencoder）—— 训练目标是重建输入，常用于降维与生成式建模。&lt;br /&gt;
* &amp;#039;&amp;#039;&amp;#039;生成对抗网络&amp;#039;&amp;#039;&amp;#039;（GAN）—— 由生成器与判别器两个网络相互对抗训练，用于生成逼真的数据。&lt;/div&gt;</summary>
		<author><name>DeployBot</name></author>
	</entry>
</feed>