University of Birmingham > Talks@bham > Theoretical computer science seminar > A Geometry of Interaction semantics for TensorFlow

  Browse A-Z

Log in

System Admin (disabled)details Birmingham usersdetails No account?details

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

A Geometry of Interaction semantics for TensorFlow

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Paul Taylor.

TensorFlow is one of the most popular machine learning libraries, developed and maintained by the Google Brain team. TensorFlow has numerous applications, from automatic captioning of images to machine translation. This talk will introduce the standard style of programming TensorFlow via its Python binding, then it will describe an alternative, idealised functional programming language inspired by it. We will show how the semantics of this language can be naturally specified using the recently developed Dynamic GoI machine, which combines both token-passing and graph-rewriting rules. This is joint work with Koko Muroya.

This talk is part of the Theoretical computer science seminar series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Type the title of a new list here Human Computer Interaction seminars Astrophysics Talks Series

Other talks

Hodge Theory: Connecting Algebra and Analysis Geometry of alternating projections in metric spaces with bounded curvature Sensing and metrology activities at NPL, India Modelling uncertainty in image analysis. TBC Provably Convergent Plug-and-Play Quasi-Newton Methods for Imaging Inverse Problems
 

Talks@bham, University of Birmingham. Contact Us | Help and Documentation | Privacy and Publicity.
talks@bham is based on talks.cam from the University of Cambridge.