2018
Previous editions: 2017 | 2016 | 2015 | 2014
Mike Innes, Deniz Yuret, and Pontus Stenetorp

Julia Computing, Koç University, and University College London



Machine Learning with Julia: Elegance, Speed and Ease

Machine Learning (ML) is at its core the art of programming by data, rather than by hand, and ML has risen to become one of the most desirable skills in academia and industry. The common maxim is that two traits control who rules the ML landscape, ability to find and ingest more data and those that can innovate the quickest. Given these traits, we argue that Julia is uniquely poised as a very strong contender as the language for ML; as we allow for quick development cycles and offer unrivalled speed. After a quick introduction to the basics of ML, we will give the audience a description of the lay of the land in terms of libraries and frameworks in Julia, and finally proceed to build simple to complex models using the premier framework Flux. After attending the workshop the audience will be familiar with the basics of ML to avoid common pitfalls and be ready to tackle their own ML problems the Julian way.

Speaker's bio

Mike Innes is a software engineer at Julia Computing, where he works on among other things the Juno IDE and the machine learning ecosystem. He is the creator of the Flux machine learning library.

Deniz Yuret is an associate professor of Computer Engineering at Koç University in Istanbul working at the Artificial Intelligence Laboratory, as well as a long-time Julia contributor and original creator of the deep learning framework Knet.

Pontus Stenetorp is a senior research associate at University College London, where he spends most of his research time on natural language processing and machine learning.

Resources