Sequence Models and the RNN API (TensorFlow Dev Summit 2017)

Subscribers:
2,510,000
Published on ● Video Link: https://www.youtube.com/watch?v=RIR_-Xlbp7s



Duration: 32:19
44,783 views
441


In this talk, Eugene Brevdo discusses the creation of flexible and high-performance sequence-to-sequence models. He covers reading and batching sequence data, the RNN API, fully dynamic calculation, fused RNN cells for optimizations for special cases, and dynamic decoding.

Visit the TensorFlow website for all session recordings: https://goo.gl/bsYmza

Subscribe to the Google Developers channel at http://goo.gl/mQyv5L


event: TensorFlow Dev Summit 2017; re_ty: Publish;







Tags:
Google
developers
Product: Web
Fullname: Other
Team: Scalable Advocacy
GDS: Full Production
Location: MTV
TensorFlow
Tensor Flow
Dev Summit
Dev
Summit
Livestream
Machine Learning
RNN API
API
Sequence
Sequence Models