Past Project: Time-series Anomaly Detection Using Recurrent Neural Nets

I'm researching ways to generally model time series with recurrent neural networks. After modeling the time series, I want to see how well the model can be used for anomaly detection. On the way to that, I want to see the effect of adding depth to the net helps in modeling.

To implement this, I'm using theano-nets and contributing to it (mostly by testing).

I will tag posts related to this with 'tsad'.