http://deeplearning.stanford.edu/wiki/index.php?title=Neural_Networks&feed=atom&action=historyNeural Networks - Revision history2024-03-29T13:50:55ZRevision history for this page on the wikiMediaWiki 1.16.2http://deeplearning.stanford.edu/wiki/index.php?title=Neural_Networks&diff=2255&oldid=prevWikiroot at 19:38, 6 April 20132013-04-06T19:38:37Z<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 19:38, 6 April 2013</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 145:</td>
<td colspan="2" class="diff-lineno">Line 145:</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>{{Sparse_Autoencoder}}</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>{{Sparse_Autoencoder}}</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>{{Languages|神经网络|中文}}</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>{{Languages|神经网络|中文}}</div></td></tr>
</table>Wikiroothttp://deeplearning.stanford.edu/wiki/index.php?title=Neural_Networks&diff=2254&oldid=prevWikiroot at 19:38, 6 April 20132013-04-06T19:38:18Z<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 19:38, 6 April 2013</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 145:</td>
<td colspan="2" class="diff-lineno">Line 145:</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>{{Sparse_Autoencoder}}</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>{{Sparse_Autoencoder}}</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>{{Languages|神经网络|中文}}</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>{{Languages|神经网络|中文}}</div></td></tr>
</table>Wikiroothttp://deeplearning.stanford.edu/wiki/index.php?title=Neural_Networks&diff=2253&oldid=prevWikiroot at 19:37, 6 April 20132013-04-06T19:37:21Z<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 19:37, 6 April 2013</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 145:</td>
<td colspan="2" class="diff-lineno">Line 145:</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>{{Sparse_Autoencoder}}</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>{{Sparse_Autoencoder}}</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|神经网络|中文}}</ins></div></td></tr>
</table>Wikiroothttp://deeplearning.stanford.edu/wiki/index.php?title=Neural_Networks&diff=871&oldid=prevWatsuen at 10:50, 26 May 20112011-05-26T10:50:10Z<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 10:50, 26 May 2011</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 142:</td>
<td colspan="2" class="diff-lineno">Line 142:</td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>patient, and the different outputs <math>y_i</math>'s might indicate presence or absence</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>patient, and the different outputs <math>y_i</math>'s might indicate presence or absence</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>of different diseases.)</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>of different diseases.)</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>{{Sparse_Autoencoder}}</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>{{Sparse_Autoencoder}}</div></td></tr>
</table>Watsuenhttp://deeplearning.stanford.edu/wiki/index.php?title=Neural_Networks&diff=867&oldid=prevWatsuen at 10:48, 26 May 20112011-05-26T10:48:28Z<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 10:48, 26 May 2011</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 142:</td>
<td colspan="2" class="diff-lineno">Line 142:</td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>patient, and the different outputs <math>y_i</math>'s might indicate presence or absence</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>patient, and the different outputs <math>y_i</math>'s might indicate presence or absence</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>of different diseases.)</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>of different diseases.)</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;">{{Sparse_Autoencoder}}</ins></div></td></tr>
</table>Watsuenhttp://deeplearning.stanford.edu/wiki/index.php?title=Neural_Networks&diff=713&oldid=prev68.65.167.109 at 05:10, 11 May 20112011-05-11T05:10:14Z<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 05:10, 11 May 2011</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 39:</td>
<td colspan="2" class="diff-lineno">Line 39:</td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div><math>[-1,1]</math> instead of <math>[0,1]</math>.</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div><math>[-1,1]</math> instead of <math>[0,1]</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>Note that some other venues (including the OpenClassroom videos, and parts of CS229), we are not using the convention</div></td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div>Note that <ins class="diffchange diffchange-inline">unlike </ins>some other venues (including the OpenClassroom videos, and parts of CS229), we are not using the convention</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>here of <math>x_0=1</math>. Instead, the intercept term is handled separately by the parameter <math>b</math>.</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>here of <math>x_0=1</math>. Instead, the intercept term is handled separately by the parameter <math>b</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>
</table>68.65.167.109http://deeplearning.stanford.edu/wiki/index.php?title=Neural_Networks&diff=347&oldid=prevAng at 20:57, 22 April 20112011-04-22T20:57:16Z<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 20:57, 22 April 2011</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 129:</td>
<td colspan="2" class="diff-lineno">Line 129:</td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>example of a '''feedforward''' neural network, since the connectivity graph</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>example of a '''feedforward''' neural network, since the connectivity graph</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>does not have any directed loops or cycles.</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>does not have any directed loops or cycles.</div></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;">%We will write <math>\textstyle s_l</math> to denote the</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;">%number of units in layer <math>\textstyle l</math> of the network (not counting the bias unit).</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>Anghttp://deeplearning.stanford.edu/wiki/index.php?title=Neural_Networks&diff=346&oldid=prevAng at 20:55, 22 April 20112011-04-22T20:55:23Z<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 20:55, 22 April 2011</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 64:</td>
<td colspan="2" class="diff-lineno">Line 64:</td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>node). The middle layer of nodes is called the '''hidden layer''', because its</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>node). The middle layer of nodes is called the '''hidden layer''', because its</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>values are not observed in the training set. We also say that our example</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>values are not observed in the training set. We also say that our example</div></td></tr>
<tr><td class='diff-marker'>-</td><td style="background: #ffa; color:black; font-size: smaller;"><div>neural network has 3 '''<del class="diffchange diffchange-inline">in put </del>units''' (not counting the bias unit), 3 </div></td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div>neural network has 3 '''<ins class="diffchange diffchange-inline">input </ins>units''' (not counting the bias unit), 3 </div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>'''hidden units''', and 1 '''output unit'''.</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>'''hidden units''', and 1 '''output unit'''.</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>
</table>Anghttp://deeplearning.stanford.edu/wiki/index.php?title=Neural_Networks&diff=345&oldid=prevAng at 20:54, 22 April 20112011-04-22T20:54:27Z<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 20:54, 22 April 2011</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 39:</td>
<td colspan="2" class="diff-lineno">Line 39:</td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div><math>[-1,1]</math> instead of <math>[0,1]</math>.</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div><math>[-1,1]</math> instead of <math>[0,1]</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>Note that <del class="diffchange diffchange-inline">unlike CS221 and </del>(parts of<del class="diffchange diffchange-inline">) </del>CS229, we are not using the convention</div></td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div>Note that <ins class="diffchange diffchange-inline">some other venues </ins>(<ins class="diffchange diffchange-inline">including the OpenClassroom videos, and </ins>parts of CS229<ins class="diffchange diffchange-inline">)</ins>, <ins class="diffchange diffchange-inline"> </ins>we are not using the convention</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>here of <math>x_0=1</math>. Instead, the intercept term is handled separately by the parameter <math>b</math>.</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>here of <math>x_0=1</math>. Instead, the intercept term is handled separately by the parameter <math>b</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>
</table>Anghttp://deeplearning.stanford.edu/wiki/index.php?title=Neural_Networks&diff=55&oldid=prevAng at 06:38, 27 February 20112011-02-27T06:38:51Z<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 06:38, 27 February 2011</td>
</tr><tr><td colspan="2" class="diff-lineno">Line 31:</td>
<td colspan="2" class="diff-lineno">Line 31:</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> </div></td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins class="diffchange diffchange-inline"><div align=center></ins></div></td></tr>
<tr><td class='diff-marker'>-</td><td style="background: #ffa; color:black; font-size: smaller;"><div>[[Image:Sigmoid_Function.png|400px|<del class="diffchange diffchange-inline">center</del>|Sigmoid activation function.]]</div></td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div>[[Image:Sigmoid_Function.png|400px|<ins class="diffchange diffchange-inline">top</ins>|Sigmoid activation function.]]</div></td></tr>
<tr><td class='diff-marker'>-</td><td style="background: #ffa; color:black; font-size: smaller;"><div>[[Image:Tanh_Function.png|400px|<del class="diffchange diffchange-inline">center</del>|Tanh activation function.]]</div></td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div>[[Image:Tanh_Function.png|400px|<ins class="diffchange diffchange-inline">top</ins>|Tanh activation function.]]</div></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div><ins class="diffchange diffchange-inline"></div></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>The <math>\tanh(z)</math> function is a rescaled version of the sigmoid, and its output range is</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>The <math>\tanh(z)</math> function is a rescaled version of the sigmoid, and its output range is</div></td></tr>
<tr><td colspan="2" class="diff-lineno">Line 63:</td>
<td colspan="2" class="diff-lineno">Line 64:</td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>node). The middle layer of nodes is called the '''hidden layer''', because its</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>node). The middle layer of nodes is called the '''hidden layer''', because its</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>values are not observed in the training set. We also say that our example</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>values are not observed in the training set. We also say that our example</div></td></tr>
<tr><td class='diff-marker'>-</td><td style="background: #ffa; color:black; font-size: smaller;"><div>neural network has 3 '''<del class="diffchange diffchange-inline">input </del>units''' (not counting the bias unit), 3 </div></td><td class='diff-marker'>+</td><td style="background: #cfc; color:black; font-size: smaller;"><div>neural network has 3 '''<ins class="diffchange diffchange-inline">in put </ins>units''' (not counting the bias unit), 3 </div></td></tr>
<tr><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>'''hidden units''', and 1 '''output unit'''.</div></td><td class='diff-marker'> </td><td style="background: #eee; color:black; font-size: smaller;"><div>'''hidden units''', and 1 '''output unit'''.</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>
</table>Ang