“FIN Status Report 2017-2-20”版本间的差异

give a talk about understanding deep learning.
try RMSProp optimizer, weight decay and obtain smooth predicted sequences.
try industry stock and obtain high correlation predicted sequence.
try to add index data and obtain more accuracy predicted value.

test our strategy
1. impact of the optimizer
2. impact of the clipping
3. investigate the volatility problem on noisy cosine.
4. improve our strategy.
5.different stock set.

make a view in mysql , handle undating data and choose the stable stock

multiple factor analysis

Implement: regularization: L2-norm, dropout, batch normalization(including some bugs) filters: MA, wavelet Implement index data. Improve strategy.

Improve strategy.