Skip to content

The Julia Programming Language and Differentiable Programming in Julia

Date: 2018-10-23
Time: 15:00
Venue: M830对面会议室
Speaker: Dr. Elliot Saba

research engineer at Julia Computing


The Julia Programming Language: The Julia language defies the typical tradeoff of high performance against high-level features. Providing the best of bothworlds through intelligent language design and modern compiler technology, Julia forms the foundation for a thriving ecosystem of packages for machinelearning, data science, parallel/heterogenous computing, data visualization, scientific analysis and more. Elliot Saba, a Senior Research Engineer at JuliaComputing will give an overview of the Julia language and why it is able to give both a pleasant and productive programming experience while still achievingspeeds competitive with best-in-class languages such as C/C++/Fortran.

Flux.jl - Differentiable Programming in Julia: Deep learning has revolutionized the fields of machine learning, computer vision, natural language processingand more. In this talk, we will explore an implementation of the basic tool of deep learning, differentiable programming, and show how integrating this tool at abasic level within a language provides an extremely simple, flexible and extensible environment for machine learning. We will start from the basics ofdifferentiable programming, step quickly through some basic machine learning theory, then show how easy it is to build new and exciting machine learningarchitectures in such an environment when the language itself supports the basic building blocks necessary for differentiable programming.


联系人:刘金国 T03组博士后 (Tel:15195955770)王磊 T03组副研究员 (Tel: 13661252980)