Title: Differentiate Everything: a lesson from deep learning
Abstract: Deep learning taught us a new way to play with computers: compose differentiable components into a computer program, then tune its parameters via gradient optimization until that program achieves what we want. This is the key idea of differentiable programming. The rapid development of deep learning technology offers convenient tools for differentiable programming, and also opens a new frontier for computational physics. I will introduce the basic notions of differentiable programming and its physics applications including modelling, optimization, control, and inverse design.
Talk – Video
Talk – Slides
Leave a Comment
Last Updated: 19th November 2020 by Denjoe O'Connor
Lei Wang (Chinese Academy of Sciences, Beijing)
Title: Differentiate Everything: a lesson from deep learning
Abstract: Deep learning taught us a new way to play with computers: compose differentiable components into a computer program, then tune its parameters via gradient optimization until that program achieves what we want. This is the key idea of differentiable programming. The rapid development of deep learning technology offers convenient tools for differentiable programming, and also opens a new frontier for computational physics. I will introduce the basic notions of differentiable programming and its physics applications including modelling, optimization, control, and inverse design.
Talk – Video
Talk – Slides
Category: Uncategorised
Recent Posts
International physics conference, hosted by DIAS, seeks to address gender equality
DIAS Astrophotography competition goes mobile for 2024
Irish scientists are part of groundbreaking discovery with James Webb Space Telescope
Dr Pauline Gagnon (formerly of CERN) to deliver two talks at DIAS
DIAS Professor announced as next President of the European Southern Observatory’s Council
Language switcher