Swift for TensorFlow: A next-generation framework for differential programming
Who is this presentation for?ML practitioners, engineers, and researchers with a variety of
Have you ever wanted to take the derivative of a dynamic program, or a Monte Carlo Tree Search? Have you ever wanted to write your own kernels? Are you sometimes bewildered by the massive API surface and complexity of modern deep learning frameworks?
The Swift for TensorFlow project is a next-generation framework for machine learning and differential computation. For instance, it includes a source-to-source auto-differentiation system that is built-into the Swift language itself, resulting in a far more flexible and powerful toolchain.
This talk will cover why Swift, the benefits of the Swift for TensorFlow project, and finally how to use Swift for TensorFlow in your own projects and applications.
Prerequisite knowledgeBasic familiarity with deep learning concepts.
What you'll learnAudience members should learn: (1) when they should consider Swift for TensorFlow (its strengths and weaknesses), (2) how to leverage the Swift for TensorFlow toolchain in their own projects, applications, and research.
Brennan Saeta is a software engineer on the Google Brain team leading the Swift for TensorFlow project. He previously was the TensorFlow tech lead for Cloud TPUs.
Leave a Comment or Question
Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?
Join the conversation here (requires login)
Diversity and Inclusion Sponsor
R & D and Innovation Track Sponsor
For conference registration information and customer service
For more information on community discounts and trade opportunities with O’Reilly conferences
For information on exhibiting or sponsoring a conference
View a complete list of O'Reilly AI contacts