Dongxu Zhang 2015-08-31 - 版本历史

2015年9月1日 (二) 11:32 Zhangdx

2015-09-01T11:32:18Z

Zhangdx：/* Work done in this week */

2015-09-01T02:47:15Z

‎Work done in this week

Zhangdx：/* Work done in this week */

2015-09-01T02:46:12Z

‎Work done in this week

Zhangdx：/* Work done in this week */

2015-09-01T02:42:56Z

‎Work done in this week

Zhangdx：/* Work done in this week */

2015-09-01T02:42:38Z

‎Work done in this week

Zhangdx：以“=== Work done in this week === * review papers on bayesian graph, document classification. * find out some interesting directions. (1)A more bayesian prior distrib...”为内容创建页面

2015-09-01T02:42:04Z

以“=== Work done in this week === * review papers on bayesian graph, document classification. * find out some interesting directions. (1)A more bayesian prior distrib...”为内容创建页面

新页面

=== Work done in this week ===
* review papers on bayesian graph, document classification.
* find out some interesting directions.
(1)A more bayesian prior distribution over neural networks, that we can give constraint on a hidden layer so that the hidden layers follows a guassian distribution with a more reasonable mean value, which may be a direction of AAAI.

(2)sequential label learning, which can be a further work with Chaoyuan.

(3)A new topic model, the code is done, still need to speed up.

(4)unbalanced autoencoder, haven't considered in details.
* Discuss ideas with Tianyi on RS and finally decide a direction, which is a deep UV structure with content knowledge.
* help Chaoyuan do the baseline reproduction.
=== Plan to do next week ===
* Compare the performance with and without topic distribution constraint. Try adding constraint on different layers.

@@ 第5行： / 第5行： @@
       layers follows a guassian distribution with a more reasonable mean value, which may be a direction of AAAI.
    (2)sequential label learning, which can be a further work with Chaoyuan.
-   (3)Try a new topic model,which is similar to cbow with large window size, the code is done, still need to speed up.
+   (3)Try a new topic model, which is similar to cbow with large window size, the code is done, still need to speed up.
    (4)unbalanced autoencoder, haven't considered in details.
 * Discussed ideas with Tianyi on RS and finally chose a direction, which is a deep UV structure with content knowledge.
 * helped Chaoyuan do the baseline reproduction.

@@ 第1行： / 第1行： @@
 === Work done in this week ===
-* review papers on bayesian graph, document classification.
+* reviewed papers on bayesian graph, document classification.
-* find out some interesting directions.
+* found out some interesting directions.
    (1)A more bayesian prior distribution over neural networks, that we can give constraint on a hidden layer so that the hidden
       layers follows a guassian distribution with a more reasonable mean value, which may be a direction of AAAI.
@@ 第7行： / 第7行： @@
    (3)Try a new topic model,which is similar to cbow with large window size, the code is done, still need to speed up.
    (4)unbalanced autoencoder, haven't considered in details.
-* Discuss ideas with Tianyi on RS and finally decide a direction, which is a deep UV structure with content knowledge.
+* Discussed ideas with Tianyi on RS and finally chose a direction, which is a deep UV structure with content knowledge.
-* help Chaoyuan do the baseline reproduction.
+* helped Chaoyuan do the baseline reproduction.
 === Plan to do next week ===
 * Compare the performance with and without topic distribution constraint. Try adding constraint on different layers.