https://marovi.ai/index.php?action=history&feed=atom&title=Translations%3ANeural_Networks%2F20%2Fzh 2026-04-28T03:30:05Z Revision history for this page on the wiki MediaWiki 1.39.1 https://marovi.ai/index.php?title=Translations:Neural_Networks/20/zh&diff=17917&oldid=prev 2026-04-27T23:40:59Z

<p>Batch translate Neural Networks unit 20 → zh</p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 23:40, 27 April 2026</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l1">Line 1:</td> <td colspan="2" class="diff-lineno">Line 1:</td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="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;"><div>&#039;&#039;&#039;通用逼近定理&#039;&#039;&#039;（Cybenko <del style="font-weight: bold; text-decoration: none;">1989, Hornik 1991）指出，具有单一隐藏层并包含有限数量神经元的前馈网络可以以任意精度逼近 </del>&lt;math&gt;\mathbb{R}^n&lt;/math&gt; <del style="font-weight: bold; text-decoration: none;">紧致子集上的任何连续函数，前提是激活函数满足温和的条件（例如非常数、有界且连续）。</del></div></td><td class="diff-marker" data-marker="+"></td><td style="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;"><div>&#039;&#039;&#039;通用逼近定理&#039;&#039;&#039;（Cybenko <ins style="font-weight: bold; text-decoration: none;">1989，Hornik 1991）指出，含有有限数量神经元的单隐藏层前馈网络可以在 </ins>&lt;math&gt;\mathbb{R}^n&lt;/math&gt; <ins style="font-weight: bold; text-decoration: none;">的任意紧子集上以任意精度逼近任何连续函数，只要{{Term|activation function|激活函数}}满足温和的条件（例如非常数、有界且连续）。</ins></div></td></tr> <!-- diff cache key mediawiki:diff::1.12:old-14855:rev-17917 --> </table>

DeployBot https://marovi.ai/index.php?title=Translations:Neural_Networks/20/zh&diff=14855&oldid=prev 2026-04-27T22:02:59Z

<p>Batch translate Neural Networks unit 20 → zh</p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 22:02, 27 April 2026</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l1">Line 1:</td> <td colspan="2" class="diff-lineno">Line 1:</td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="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;"><div>&#039;&#039;&#039;通用逼近定理&#039;&#039;&#039;（Cybenko <del style="font-weight: bold; text-decoration: none;">1989，Hornik 1991）指出，具有有限数量神经元的单隐藏层前馈网络可以以任意精度逼近 </del>&lt;math&gt;\mathbb{R}^n&lt;/math&gt; <del style="font-weight: bold; text-decoration: none;">紧子集上的任何连续函数，前提是激活函数满足温和的条件（例如，非常数、有界且连续）。</del></div></td><td class="diff-marker" data-marker="+"></td><td style="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;"><div>&#039;&#039;&#039;通用逼近定理&#039;&#039;&#039;（Cybenko <ins style="font-weight: bold; text-decoration: none;">1989, Hornik 1991）指出，具有单一隐藏层并包含有限数量神经元的前馈网络可以以任意精度逼近 </ins>&lt;math&gt;\mathbb{R}^n&lt;/math&gt; <ins style="font-weight: bold; text-decoration: none;">紧致子集上的任何连续函数，前提是激活函数满足温和的条件（例如非常数、有界且连续）。</ins></div></td></tr> <!-- diff cache key mediawiki:diff::1.12:old-5329:rev-14855 --> </table>

DeployBot https://marovi.ai/index.php?title=Translations:Neural_Networks/20/zh&diff=5329&oldid=prev 2026-04-27T03:35:02Z

<p>Batch translate Neural Networks unit 20 → zh</p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 03:35, 27 April 2026</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l1">Line 1:</td> <td colspan="2" class="diff-lineno">Line 1:</td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="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;"><div>&#039;&#039;&#039;<del style="font-weight: bold; text-decoration: none;">通用近似定理</del>&#039;&#039;&#039;<del style="font-weight: bold; text-decoration: none;">（universal approximation theorem，Cybenko </del>1989，Hornik <del style="font-weight: bold; text-decoration: none;">1991）指出：在 </del>&lt;math&gt;\mathbb{R}^n&lt;/math&gt; <del style="font-weight: bold; text-decoration: none;">上的紧致子集上，只要激活函数满足温和条件（例如非常数、有界且连续），具有有限个神经元的单隐藏层前馈网络便能以任意精度逼近任何连续函数。</del></div></td><td class="diff-marker" data-marker="+"></td><td style="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;"><div>&#039;&#039;&#039;<ins style="font-weight: bold; text-decoration: none;">通用逼近定理</ins>&#039;&#039;&#039;<ins style="font-weight: bold; text-decoration: none;">（Cybenko </ins>1989，Hornik <ins style="font-weight: bold; text-decoration: none;">1991）指出，具有有限数量神经元的单隐藏层前馈网络可以以任意精度逼近 </ins>&lt;math&gt;\mathbb{R}^n&lt;/math&gt; <ins style="font-weight: bold; text-decoration: none;">紧子集上的任何连续函数，前提是激活函数满足温和的条件（例如，非常数、有界且连续）。</ins></div></td></tr> <!-- diff cache key mediawiki:diff::1.12:old-2300:rev-5329 --> </table>

DeployBot https://marovi.ai/index.php?title=Translations:Neural_Networks/20/zh&diff=2300&oldid=prev 2026-04-27T00:25:18Z

<p>[deploy-bot] Translate Neural Networks unit 20 to zh</p> <p><b>New page</b></p><div>&#039;&#039;&#039;通用近似定理&#039;&#039;&#039;（universal approximation theorem，Cybenko 1989，Hornik 1991）指出：在 &lt;math&gt;\mathbb{R}^n&lt;/math&gt; 上的紧致子集上，只要激活函数满足温和条件（例如非常数、有界且连续），具有有限个神经元的单隐藏层前馈网络便能以任意精度逼近任何连续函数。</div>

DeployBot