http://deeplearning.stanford.edu/wiki/index.php?title=Softmax%E5%9B%9E%E5%BD%92&feed=atom&action=history
Softmax回归 - Revision history
2024-03-29T01:51:45Z
Revision history for this page on the wiki
MediaWiki 1.16.2
http://deeplearning.stanford.edu/wiki/index.php?title=Softmax%E5%9B%9E%E5%BD%92&diff=2360&oldid=prev
Wikiroot at 05:38, 8 April 2013
2013-04-08T05:38:38Z
<p></p>
<table style="background-color: white; color:black;">
<col class='diff-marker' />
<col class='diff-content' />
<col class='diff-marker' />
<col class='diff-content' />
<tr valign='top'>
<td colspan='2' style="background-color: white; color:black;">← Older revision</td>
<td colspan='2' style="background-color: white; color:black;">Revision as of 05:38, 8 April 2013</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 223:</td>
<td colspan="2" class="diff-lineno">Line 223:</td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>在第一个例子中,三个类别是互斥的,因此更适于选择softmax回归分类器 。而在第二个例子中,建立三个独立的 logistic回归分类器更加合适。</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>在第一个例子中,三个类别是互斥的,因此更适于选择softmax回归分类器 。而在第二个例子中,建立三个独立的 logistic回归分类器更加合适。</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'>-</td><td style="background: #ffa; color:black; font-size: smaller;"><div><del style="color: red; font-weight: bold; text-decoration: none;"></del></div></td><td colspan="2"> </td></tr>
<tr><td class='diff-marker'>-</td><td style="background: #ffa; color:black; font-size: smaller;"><div><del style="color: red; font-weight: bold; text-decoration: none;">{{Softmax}}</del></div></td><td colspan="2"> </td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
</table>
Wikiroot
http://deeplearning.stanford.edu/wiki/index.php?title=Softmax%E5%9B%9E%E5%BD%92&diff=2336&oldid=prev
Wikiroot at 05:08, 8 April 2013
2013-04-08T05:08:56Z
<p></p>
<table style="background-color: white; color:black;">
<col class='diff-marker' />
<col class='diff-content' />
<col class='diff-marker' />
<col class='diff-content' />
<tr valign='top'>
<td colspan='2' style="background-color: white; color:black;">← Older revision</td>
<td colspan='2' style="background-color: white; color:black;">Revision as of 05:08, 8 April 2013</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 246:</td>
<td colspan="2" class="diff-lineno">Line 246:</td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>曾俊瑀(knighterzjy@gmail.com), 王方(fangkey@gmail.com),王文中(wangwenzhong@ymail.com)</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>曾俊瑀(knighterzjy@gmail.com), 王方(fangkey@gmail.com),王文中(wangwenzhong@ymail.com)</div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;">{{Softmax回归}}</ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>{{Languages|Softmax_Regression|English}}</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>{{Languages|Softmax_Regression|English}}</div></td></tr>
</table>
Wikiroot
http://deeplearning.stanford.edu/wiki/index.php?title=Softmax%E5%9B%9E%E5%BD%92&diff=2287&oldid=prev
Kandeng at 13:24, 7 April 2013
2013-04-07T13:24:13Z
<p></p>
<table style="background-color: white; color:black;">
<col class='diff-marker' />
<col class='diff-content' />
<col class='diff-marker' />
<col class='diff-content' />
<tr valign='top'>
<td colspan='2' style="background-color: white; color:black;">← Older revision</td>
<td colspan='2' style="background-color: white; color:black;">Revision as of 13:24, 7 April 2013</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 246:</td>
<td colspan="2" class="diff-lineno">Line 246:</td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>曾俊瑀(knighterzjy@gmail.com), 王方(fangkey@gmail.com),王文中(wangwenzhong@ymail.com)</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>曾俊瑀(knighterzjy@gmail.com), 王方(fangkey@gmail.com),王文中(wangwenzhong@ymail.com)</div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;">{{Languages|Softmax_Regression|English}}</ins></div></td></tr>
</table>
Kandeng
http://deeplearning.stanford.edu/wiki/index.php?title=Softmax%E5%9B%9E%E5%BD%92&diff=2224&oldid=prev
Kandeng at 15:28, 5 April 2013
2013-04-05T15:28:21Z
<p></p>
<table style="background-color: white; color:black;">
<col class='diff-marker' />
<col class='diff-content' />
<col class='diff-marker' />
<col class='diff-content' />
<tr valign='top'>
<td colspan='2' style="background-color: white; color:black;">← Older revision</td>
<td colspan='2' style="background-color: white; color:black;">Revision as of 15:28, 5 April 2013</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 222:</td>
<td colspan="2" class="diff-lineno">Line 222:</td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>在第一个例子中,三个类别是互斥的,因此更适于选择softmax回归分类器 。而在第二个例子中,建立三个独立的 logistic回归分类器更加合适。</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>在第一个例子中,三个类别是互斥的,因此更适于选择softmax回归分类器 。而在第二个例子中,建立三个独立的 logistic回归分类器更加合适。</div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;">{{Softmax}}</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>==中英文对照==</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>==中英文对照==</div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>:Softmax回归 Softmax Regression</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>:Softmax回归 Softmax Regression</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>:有监督学习 supervised learning</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>:有监督学习 supervised learning</div></td></tr>
</table>
Kandeng
http://deeplearning.stanford.edu/wiki/index.php?title=Softmax%E5%9B%9E%E5%BD%92&diff=2044&oldid=prev
Kandeng at 02:42, 29 March 2013
2013-03-29T02:42:07Z
<p></p>
<table style="background-color: white; color:black;">
<col class='diff-marker' />
<col class='diff-content' />
<col class='diff-marker' />
<col class='diff-content' />
<tr valign='top'>
<td colspan='2' style="background-color: white; color:black;">← Older revision</td>
<td colspan='2' style="background-color: white; color:black;">Revision as of 02:42, 29 March 2013</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 223:</td>
<td colspan="2" class="diff-lineno">Line 223:</td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>在第一个例子中,三个类别是互斥的,因此更适于选择softmax回归分类器 。而在第二个例子中,建立三个独立的 logistic回归分类器更加合适。</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>在第一个例子中,三个类别是互斥的,因此更适于选择softmax回归分类器 。而在第二个例子中,建立三个独立的 logistic回归分类器更加合适。</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;">==中英文对照==</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;">:Softmax回归 Softmax Regression</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;">:有监督学习 supervised learning</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;">:无监督学习 unsupervised learning</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;">:深度学习 deep learning</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;">:logistic回归 logistic regression</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;">:截距项 intercept term</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;">:二元分类 binary classification</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;">:类型标记 class labels</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;">:估值函数/估计值 hypothesis</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;">:代价函数 cost function</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;">:多元分类 multi-class classification</ins></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;">:权重衰减 weight decay</ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
</table>
Kandeng
http://deeplearning.stanford.edu/wiki/index.php?title=Softmax%E5%9B%9E%E5%BD%92&diff=2043&oldid=prev
Kandeng at 02:27, 29 March 2013
2013-03-29T02:27:10Z
<p></p>
<table style="background-color: white; color:black;">
<col class='diff-marker' />
<col class='diff-content' />
<col class='diff-marker' />
<col class='diff-content' />
<tr valign='top'>
<td colspan='2' style="background-color: white; color:black;">← Older revision</td>
<td colspan='2' style="background-color: white; color:black;">Revision as of 02:27, 29 March 2013</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 108:</td>
<td colspan="2" class="diff-lineno">Line 108:</td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'>-</td><td style="background: #ffa; color:black; font-size: smaller;"><div>== <del class="diffchange diffchange-inline">softmax回归模型参数化的特点</del>==</div></td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div>== <ins class="diffchange diffchange-inline">Softmax回归模型参数化的特点</ins>==</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>Softmax 回归有一个不寻常的特点:它有一个“冗余”的参数集。为了便于阐述这一特点,假设我们从参数向量 <math>\textstyle \theta_j</math> 中减去了向量 <math>\textstyle \psi</math>,这时,每一个 <math>\textstyle \theta_j</math> 都变成了 <math>\textstyle \theta_j - \psi</math>(<math>\textstyle j=1, \ldots, k</math>)。此时假设函数变成了以下的式子:</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>Softmax 回归有一个不寻常的特点:它有一个“冗余”的参数集。为了便于阐述这一特点,假设我们从参数向量 <math>\textstyle \theta_j</math> 中减去了向量 <math>\textstyle \psi</math>,这时,每一个 <math>\textstyle \theta_j</math> 都变成了 <math>\textstyle \theta_j - \psi</math>(<math>\textstyle j=1, \ldots, k</math>)。此时假设函数变成了以下的式子:</div></td></tr>
</table>
Kandeng
http://deeplearning.stanford.edu/wiki/index.php?title=Softmax%E5%9B%9E%E5%BD%92&diff=2042&oldid=prev
Kandeng at 02:26, 29 March 2013
2013-03-29T02:26:42Z
<p></p>
<table style="background-color: white; color:black;">
<col class='diff-marker' />
<col class='diff-content' />
<col class='diff-marker' />
<col class='diff-content' />
<tr valign='top'>
<td colspan='2' style="background-color: white; color:black;">← Older revision</td>
<td colspan='2' style="background-color: white; color:black;">Revision as of 02:26, 29 March 2013</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 1:</td>
<td colspan="2" class="diff-lineno">Line 1:</td></tr>
<tr><td class='diff-marker'>-</td><td style="background: #ffa; color:black; font-size: smaller;"><div><del style="color: red; font-weight: bold; text-decoration: none;"></del></div></td><td colspan="2"> </td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>==简介==</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>==简介==</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td colspan="2" class="diff-lineno">Line 60:</td>
<td colspan="2" class="diff-lineno">Line 59:</td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>\end{bmatrix}</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>\end{bmatrix}</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div></math></div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div></math></div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins style="color: red; font-weight: bold; text-decoration: none;"></ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>== 代价函数==</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>== 代价函数==</div></td></tr>
</table>
Kandeng
http://deeplearning.stanford.edu/wiki/index.php?title=Softmax%E5%9B%9E%E5%BD%92&diff=2041&oldid=prev
Kandeng at 02:25, 29 March 2013
2013-03-29T02:25:23Z
<p></p>
<table style="background-color: white; color:black;">
<col class='diff-marker' />
<col class='diff-content' />
<col class='diff-marker' />
<col class='diff-content' />
<tr valign='top'>
<td colspan='2' style="background-color: white; color:black;">← Older revision</td>
<td colspan='2' style="background-color: white; color:black;">Revision as of 02:25, 29 March 2013</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 1:</td>
<td colspan="2" class="diff-lineno">Line 1:</td></tr>
<tr><td class='diff-marker'>-</td><td style="background: #ffa; color:black; font-size: smaller;"><div><del style="color: red; font-weight: bold; text-decoration: none;"></del></div></td><td colspan="2"> </td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>==简介==</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>==简介==</div></td></tr>
<tr><td colspan="2" class="diff-lineno">Line 228:</td>
<td colspan="2" class="diff-lineno">Line 227:</td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>==中文译者==</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>==中文译者==</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'>-</td><td style="background: #ffa; color:black; font-size: smaller;"><div>@<del class="diffchange diffchange-inline">knighterzjy </del>, 王方(fangkey@gmail.com),王文中(wangwenzhong@ymail.com)</div></td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins class="diffchange diffchange-inline">曾俊瑀(knighterzjy</ins>@<ins class="diffchange diffchange-inline">gmail.com)</ins>, 王方(fangkey@gmail.com),王文中(wangwenzhong@ymail.com)</div></td></tr>
</table>
Kandeng
http://deeplearning.stanford.edu/wiki/index.php?title=Softmax%E5%9B%9E%E5%BD%92&diff=2040&oldid=prev
Kandeng at 02:21, 29 March 2013
2013-03-29T02:21:09Z
<p></p>
<a href="http://deeplearning.stanford.edu/wiki/index.php?title=Softmax%E5%9B%9E%E5%BD%92&diff=2040&oldid=1917">Show changes</a>
Kandeng
http://deeplearning.stanford.edu/wiki/index.php?title=Softmax%E5%9B%9E%E5%BD%92&diff=1917&oldid=prev
Kandeng: /* 代价函数 Cost Function */
2013-03-16T06:24:21Z
<p><span class="autocomment">代价函数 Cost Function</span></p>
<table style="background-color: white; color:black;">
<col class='diff-marker' />
<col class='diff-content' />
<col class='diff-marker' />
<col class='diff-content' />
<tr valign='top'>
<td colspan='2' style="background-color: white; color:black;">← Older revision</td>
<td colspan='2' style="background-color: white; color:black;">Revision as of 06:24, 16 March 2013</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 65:</td>
<td colspan="2" class="diff-lineno">Line 65:</td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div></math></div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div></math></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'>-</td><td style="background: #ffa; color:black; font-size: smaller;"><div>== 代价函数 <del class="diffchange diffchange-inline">Cost Function </del>==</div></td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div>== 代价函数==</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>现在我们来介绍softmax回归算法的代价函数。在下面的公式中,<math>\textstyle 1\{\cdot\}</math>是示性函数,其取值规则为:</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>现在我们来介绍softmax回归算法的代价函数。在下面的公式中,<math>\textstyle 1\{\cdot\}</math>是示性函数,其取值规则为:</div></td></tr>
</table>
Kandeng