Learning to Forget: Continual Prediction with LSTM. Gers, F. A., Schmidhuber, J., & Cummins, F. Neural Computation, 12(10):2451–2471, 2000.
bibtex   
@article{Gers:2000nc,
author = {F. A. Gers and J. Schmidhuber and F. Cummins},
title = {Learning to Forget: Continual Prediction with {LSTM}},
volume = {12}, 
number = {10}, 
pages = {2451--2471},
journal = {Neural Computation},
year =  {2000}}

Downloads: 0