This week, Ravi Krishna, from Prof. Keutzer's group in EECS, will go over the basics of Recurrent Neural Networks (RNNs and LSTMs), provide an update on the latest developments in architectures and training techniques, and conclude on some of the current challenges in this field. Ravi has been actively working on RNNs and time-series problems for over a year and will share his valuable experience with working with these models.
The Berkeley Statistics and Machine Learning Discussion Group meets weekly to discuss current applications across a wide variety of research domains and software methodologies. Register here to view, propose and vote for this group's upcoming discussion topics. All interested members of the UC Berkeley and LBL communities are welcome and encouraged to attend. Questions may be directed to François Lanusse.