Julia comes ready with Flux, a state-of-the-art framework for machine learning and AI.
As machine learning systems become more complex, researchers increasingly need differentiable languages in which they can simply write their algorithms as code. Julia’s mathematical syntax makes it an ideal way to express algorithms just as they are written in papers, while Flux turns code into trainable models with automatic differentiation, GPU acceleration and support for terabytes of data via JuliaDB.
Flux provides a highly intuitive, layer-stacking-based interface for simple models, yet you can easily write your own mathematics for more advanced ones such as variational auto-encoders. Despite how easy it is to use, Flux is the most flexible ML framework on Earth; one can easily integrate it with other Julia libraries like physics simulators or differential equations solvers, and even drop down to writing a quick CUDA kernel via CUDAnative; all from one language, or even from a single script!
Julia also has best-in-class support for other modern machine learning frameworks such as TensorFlow and MXNet, making it easy to adapt to existing workflows.
Mike Innes - Machine Learning with Julia (Flux)
At JuliaCon 2017, our very own Mike Innes gives a brief introduction to Flux.jl, a Julia package that expands Julia’s flexibility in machine learning use cases. He further goes on to show how it provides lightweight abstractions on top of Julia’s native GPU and Automatic Differentiation support, while remaining fully hackable.
Jonathan Malmaud - Modern Machine Learning in Julia with TensorFlow.jl
Another talk from JuliaCon 2017, this time from Jonathan Malmaud, an MIT researcher working on cutting edge machine learning technologies, demonstrating how Julia’s interfaces to popular Machine Learning frameworks are succinct and seamless to use, illustrated with the example of Julia’s TensorFlow.jl.
Parallel Supercomputing for Astronomy
The Celeste research team spent three years developing and testing a new parallel computing method that was used to process the Sloan Digital Sky Survey dataset and produce the most accurate catalog of 188 million astronomical objects in just 14.6 minutes with state-of-the-art point and uncertainty estimates.
Tangent Works uses Julia to build a comprehensive analytics solution that blurs the barrier between prototyping done by data
scientists and production development done by developers.
Medical Diagnosis, Source: JuliaComputing.com
Diabetic retinopathy is an eye disease that affects more than 126 million diabetics and accounts for more than 5% of blindness cases worldwide. Timely screening and diagnosis can help prevent vision loss for millions of diabetics worldwide. IBM and Julia Computing analyzed eye fundus images provided by Drishti Eye Hospitals, and a built a deep learning solution that provides eye diagnosis and care to thousands of rural Indians.
Need help with Julia?
We also provide training and consulting services
and build open source or proprietary packages
for our customers on a consulting basis. Mail us:
Julia Computing was founded by all the creators
of the language to provide commercial support
to Julia users. We are based in Boston, New York,
San Francisco, London and Bangalore with
customers across the world.
© 2016 - 2020 Julia Computing, Inc. All Rights Reserved.