Models as Code Differentiable Programming with Julia by Viral Shah #ODSC_India
Since we originally proposed the need for a first-class language, compiler and ecosystem for machine learning (ML) - a view that is increasingly shared by many, there have been plenty of interesting developments in the field. Not only have the tradeoffs in existing systems, such as TensorFlow and PyTorch, not been resolved, but they are clearer than ever now that both frameworks contain distinct "static graph" and "eager execution" interfaces. Meanwhile, the idea of ML models fundamentally being differentiable algorithms – often called differentiable programming – has caught on.
Where current frameworks fall short, several exciting new projects have sprung up that dispense with graphs entirely, to bring differentiable programming to the mainstream. Myia, by the Theano team, differentiates and compiles a subset of Python to high-performance GPU code. Swift for TensorFlow extends Swift so that compatible functions can be compiled to TensorFlow graphs. And finally, the Flux ecosystem is extending Julia’s compiler with a number of ML-focused tools, including first-class gradients, just-in-time CUDA kernel compilation, automatic batching and support for new hardware such as TPUs.
This talk will demonstrate how Julia is increasingly becoming a natural language for machine learning, the kind of libraries and applications the Julia community is building, the contributions from India (there are many!), and our plans going forward.
More details: https://confengine.com/odsc-india-2019/proposal/9539/models-as-code-differentiable-programming-with-julia
Conference Link: https://india.odsc.com
Видео Models as Code Differentiable Programming with Julia by Viral Shah #ODSC_India канала ConfEngine
Where current frameworks fall short, several exciting new projects have sprung up that dispense with graphs entirely, to bring differentiable programming to the mainstream. Myia, by the Theano team, differentiates and compiles a subset of Python to high-performance GPU code. Swift for TensorFlow extends Swift so that compatible functions can be compiled to TensorFlow graphs. And finally, the Flux ecosystem is extending Julia’s compiler with a number of ML-focused tools, including first-class gradients, just-in-time CUDA kernel compilation, automatic batching and support for new hardware such as TPUs.
This talk will demonstrate how Julia is increasingly becoming a natural language for machine learning, the kind of libraries and applications the Julia community is building, the contributions from India (there are many!), and our plans going forward.
More details: https://confengine.com/odsc-india-2019/proposal/9539/models-as-code-differentiable-programming-with-julia
Conference Link: https://india.odsc.com
Видео Models as Code Differentiable Programming with Julia by Viral Shah #ODSC_India канала ConfEngine
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![Deep Learning Powered Genomic Research by Dr. C.S.Jyothirmayee & Vijayalakshmi Mahadevan #ODSC_India](https://i.ytimg.com/vi/A0U9nme5D3M/default.jpg)
![Getting2Alpha: Turbo charge your product with Game Thinking by Amy Jo Kim](https://i.ytimg.com/vi/lofGt4g1yPM/default.jpg)
![My Journey with Erlang at Redbus by Sujatha Hemmady #FnConf19 #CBLIndia](https://i.ytimg.com/vi/pd2E9nkxHNg/default.jpg)
![Selenium has a new trick up its sleeve to track failures by Puja Jagani #SeConf 2022](https://i.ytimg.com/vi/ahLsdBw0R-Y/default.jpg)
![Retargeting F# for the web: from JS to WebAssembly by Adam Granicz #FnConf 2022](https://i.ytimg.com/vi/yPkWA74cR1Y/default.jpg)
![Art of Effective Visualization of Multi-dimensional Data by Dipanjan Sarkar at #ODSC_India](https://i.ytimg.com/vi/2yRl-DEu0g0/default.jpg)
![Building Alignment - Team Working Agreements by Ellen Grove at #AgileIndiaLite](https://i.ytimg.com/vi/pB8ANmUkWl4/default.jpg)
![Build your own Appium plugin by Sai Krishna & Srinivasan Sekar #AppiumConf2021](https://i.ytimg.com/vi/JpYpLM--atE/default.jpg)
![Edward Kmett - How I discovered functional programming](https://i.ytimg.com/vi/IMFRQmysY7U/default.jpg)
![What have you made possible with the Selenium test automation platform? [Selenium Conf 2020 CFP]](https://i.ytimg.com/vi/61pn1zLr2ZM/default.jpg)
![Navigating the loop in water on land & programming models by Bruce Tate & Francesco Cesarini #FnConf](https://i.ytimg.com/vi/6x9Sl3VO66s/default.jpg)
![How we use KPI trees to Maintain Focus on Business Outcomes - Sreekandh & Sriram #AgileIndia 2022](https://i.ytimg.com/vi/CO3cL11G0xs/default.jpg)
![Ansible meets Selenium Grid - Building a stable local iOS simulator farm by Syam Sasi #SeConf2020](https://i.ytimg.com/vi/iY4dC49kQUY/default.jpg)
![The Screenplay Pattern: Better Interactions for Better Automation by Andrew Knight #SeConf 2022](https://i.ytimg.com/vi/cwnkXPxh0wc/default.jpg)
![Fun! Done! Learn! A Positive Retrospective Born in Japan by Yasunobu Kawaguchi #AgileIndia2020](https://i.ytimg.com/vi/0ttC3HYkHfg/default.jpg)
![A Balancing Act by Dr. Anita Bhandari & Rajneesh Bhandari #AgileIndia2020](https://i.ytimg.com/vi/JovE0XPX5-E/default.jpg)
![From Hrs to Mins: How to Write Test Cases for a Faster Regression Suite by Chitvan Singh #SeConf2020](https://i.ytimg.com/vi/AiUjUDflHpE/default.jpg)
![Building Multimodal Deep learning recommendation Systems by Sujoy Roychowdhury #ODSC_India](https://i.ytimg.com/vi/67awVc0oTg8/default.jpg)
![How to successfully craft a business agility transformation? by Phil Abernathy #AgileIndia2019](https://i.ytimg.com/vi/oVpnQz2PnDY/default.jpg)
![Using Deep-Learning to Accurately Diagnose Your Broadband Connection by Nicolas Dupuis #ODSC_India](https://i.ytimg.com/vi/QO5FywW6wWc/default.jpg)