“FIN Status Report 2017-2-20”版本间的差异
来自cslt Wiki
| 第6行： | 第6行： | ||
give a talk about understanding deep learning.<br> | give a talk about understanding deep learning.<br> | ||
try RMSProp optimizer, weight decay and obtain smooth predicted sequences.<br> | try RMSProp optimizer, weight decay and obtain smooth predicted sequences.<br> | ||
| − | try industry stock and obtain | + | try industry stock and obtain highly correlated predicted sequence.<br> |
| − | try to add index data and obtain more | + | try to add index data and obtain more accurate predicted value. |
|| | || | ||
| − | + | study the stock selecting model.<br> | |
| − | + | study the architecture of the network. | |
| − | + | ||
| − | + | ||
| − | + | ||
| − | + | ||
|- | |- | ||
| Yuxin Zhang|| | | Yuxin Zhang|| | ||
2017年2月20日 (一) 08:07的版本
| People | Last Week | This Week |
|---|---|---|
| Yang Wang |
give a talk about understanding deep learning. |
study the stock selecting model. |
| Yuxin Zhang |
|
|
| Yaodong Wang |
make a view in mysql , handle undating data and choose the stable stock |
multiple factor analysis |
| Tongzheng Ren |
Implement: regularization: L2-norm, dropout, batch normalization(including some bugs) filters: MA, wavelet Implement index data. Improve strategy. |
Improve strategy. |
