http://www.cslt.org/mediawiki/index.php?action=history&feed=atom&title=Dongxu_Zhang_2015-09-14
Dongxu Zhang 2015-09-14 - 版本历史
2026-04-03T21:50:50Z
本wiki的该页面的版本历史
MediaWiki 1.23.3
http://www.cslt.org/mediawiki/index.php?title=Dongxu_Zhang_2015-09-14&diff=16794&oldid=prev
2015年9月15日 (二) 07:39 Zhangdx
2015-09-15T07:39:41Z
<p></p>
<table class='diff diff-contentalign-left'>
<col class='diff-marker' />
<col class='diff-content' />
<col class='diff-marker' />
<col class='diff-content' />
<tr style='vertical-align: top;'>
<td colspan='2' style="background-color: white; color:black; text-align: center;">←上一版本</td>
<td colspan='2' style="background-color: white; color:black; text-align: center;">2015年9月15日 (二) 07:39的版本</td>
</tr><tr><td colspan="2" class="diff-lineno">第1行：</td>
<td colspan="2" class="diff-lineno">第1行：</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>Last Week:</div></td><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>Last Week:</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color:black; 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>1. The accuracy of tfidf with 2 layer NN and softmax for classification is higher than 4 layer NN and softmax(79%, 75%).  </div></td><td class='diff-marker'>+</td><td style="color:black; 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>1. The accuracy of tfidf with 2 layer NN and softmax for classification is higher than 4 layer NN and softmax(79%, 75%). The performance on test set gets best result when training error is around 0.98.  </div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color:black; 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><del class="diffchange diffchange-inline">  </del>The performance on test set gets best result when training error is around 0.98.  </div></td><td class='diff-marker'>+</td><td style="color:black; 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></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>2. Set small lambda of joint training only made the result not that bad. (tried lambda = 0.1)</div></td><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>2. Set small lambda of joint training only made the result not that bad. (tried lambda = 0.1)</div></td></tr>
</table>
Zhangdx
http://www.cslt.org/mediawiki/index.php?title=Dongxu_Zhang_2015-09-14&diff=16793&oldid=prev
2015年9月15日 (二) 07:39 Zhangdx
2015-09-15T07:39:28Z
<p></p>
<table class='diff diff-contentalign-left'>
<col class='diff-marker' />
<col class='diff-content' />
<col class='diff-marker' />
<col class='diff-content' />
<tr style='vertical-align: top;'>
<td colspan='2' style="background-color: white; color:black; text-align: center;">←上一版本</td>
<td colspan='2' style="background-color: white; color:black; text-align: center;">2015年9月15日 (二) 07:39的版本</td>
</tr><tr><td colspan="2" class="diff-lineno">第2行：</td>
<td colspan="2" class="diff-lineno">第2行：</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>1. The accuracy of tfidf with 2 layer NN and softmax for classification is higher than 4 layer NN and softmax(79%, 75%).  </div></td><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>1. The accuracy of tfidf with 2 layer NN and softmax for classification is higher than 4 layer NN and softmax(79%, 75%).  </div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color:black; 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><del style="font-weight: bold; text-decoration: none;">  </del></div></td><td colspan="2"> </td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>   The performance on test set gets best result when training error is around 0.98.  </div></td><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"><div>   The performance on test set gets best result when training error is around 0.98.  </div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f9f9f9; color: #333333; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #e6e6e6; vertical-align: top; white-space: pre-wrap;"></td></tr>
</table>
Zhangdx
http://www.cslt.org/mediawiki/index.php?title=Dongxu_Zhang_2015-09-14&diff=16792&oldid=prev
Zhangdx：以“Last Week: 1. The accuracy of tfidf with 2 layer NN and softmax for classification is higher than 4 layer NN and softmax(79%, 75%). The performance on test s...”为内容创建页面
2015-09-15T07:39:17Z
<p>以“Last Week: 1. The accuracy of tfidf with 2 layer NN and softmax for classification is higher than 4 layer NN and softmax(79%, 75%). The performance on test s...”为内容创建页面</p>
<p><b>新页面</b></p><div>Last Week:<br />
<br />
1. The accuracy of tfidf with 2 layer NN and softmax for classification is higher than 4 layer NN and softmax(79%, 75%). <br />
<br />
The performance on test set gets best result when training error is around 0.98. <br />
<br />
2. Set small lambda of joint training only made the result not that bad. (tried lambda = 0.1)<br />
<br />
3. Tried a simple idea on Graph prediction.<br />
<br />
This Week:<br />
<br />
1. Tried features for softmax. And tried smaller lambda.<br />
<br />
2. tune the performance of transE. and check out if the idea works.<br />
<br />
3. Try sequence supervised learning. Compare with Viterbi.</div>
Zhangdx