Accelerating recurrent neural network training via two stage classes and parallelization.

Zhiheng Huang Geoffrey Zweig Michael Levit Benoît Dumoulin Barlas Oguz Shawn Chang Accelerating recurrent neural network training via two stage classes and parallelization. 326-331 2013 ASRU https://doi.org/10.1109/ASRU.2013.6707751 conf/asru/2013 db/conf/asru/asru2013.html#HuangZLDOC13