“Dongxu Zhang 2015-08-31”版本间的差异
来自cslt Wiki
（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） |
（→Work done in this week） |
||
| 第2行： | 第2行： | ||
* review papers on bayesian graph, document classification. | * review papers on bayesian graph, document classification. | ||
* find out some interesting directions. | * 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. | + | (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. | (2)sequential label learning, which can be a further work with Chaoyuan. | ||
| 第11行： | 第12行： | ||
* Discuss ideas with Tianyi on RS and finally decide a direction, which is a deep UV structure with content knowledge. | * 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. | * help Chaoyuan do the baseline reproduction. | ||
| + | |||
=== Plan to do next week === | === Plan to do next week === | ||
* Compare the performance with and without topic distribution constraint. Try adding constraint on different layers. | * Compare the performance with and without topic distribution constraint. Try adding constraint on different layers. | ||
2015年9月1日 (二) 02:42的版本
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.
