Vitaly joined NVIDIA in September, 2017 to work on efficient end-to-end Deep Learning training algorithms. Before that, he conducted applied research to solve Computer Vision problems with Deep Learning based methods at Samsung R&D Institute Russia.
Posts by Vitaly Lavrukhin
Oct 09, 2018
Mixed Precision Training for NLP and Speech Recognition with OpenSeq2Seq
The success of neural networks thus far has been built on bigger datasets, better theoretical models, and reduced training time. Sequential models, in...
11 MIN READ