University of Cambridge > Talks.cam > Microsoft Research Cambridge, public talks > Flux: Elegant Machine Learning with Julia

  Browse A-Z

Log in

University Account External (via Google)

🔐 Log In

Information on

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

ℹī¸ Information

Flux: Elegant Machine Learning with Julia

Download to your calendar using vCal

If you have a question about this talk, please contact Microsoft Research Cambridge Talks Admins .

ī‚§ Please note, this event may be recorded. Microsoft will own the copyright of any recording and reserves the right to distribute it as required.

This talk will introduce Flux, a library for machine learning (ML). Flux is written in Julia, a language designed for high-performance numerical computing, in around 1,000 lines of straightforward code. This talk will explain how to build Flux, starting with the basics of Julia and how it compiles high-level mathematical programs to tight machine code, and how the compiler can be extended to support ML.

Deep learning models have become complex, and increasingly look like “differentiable algorithms”; through this lens, ML systems problems become language and compiler problems. We illustrate how augmenting a numerical language with compiler-level automatic differentiation enables an unusually flexible and hackable approach to ML, one which provides an elegant define-by-run style while supporting new kinds of models, cutting edge hardware and state-of-the-art performance.

This talk is part of the Microsoft Research Cambridge, public talks series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Robinson College Umney Theatre in person & via zoom Todd-Hamied meeting room, Department of Chemistry

Other talks

Polar Oceans Seminar Talk Online Causal Inference Seminar Title TBC Morning Break / Group Photo Title to be confirmed A Novel Diffusion Model based Approach for Sleep Music Generation
 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity