Uploaded January 2026 | Updated November 2026, 3 hours ago
In this insightful talk, Valentin Churavy (University of Augsburg) explores differentiable programming and how the Enzyme automatic differentiation framework brings powerful derivative capabilities to scientific computing workflows in Julia.
What this session covers:
• An introduction to how Enzyme enables differentiable programming by generating derivatives of complex scientific code patterns — even those involving mutation and control flow — directly from LLVM IR.
• Why differentiable programming is becoming essential in modern scientific computing, especially where gradients are needed for optimization, sensitivity analysis, and matrix-free methods.
• Demonstrations of how Enzyme integrates with Julia’s scientific ecosystem, empowering users to take derivatives of high-performance simulations without rewriting code.
Whether you’re into scientific simulations, automatic differentiation, or advanced Julia workflows, this talk gives a practical and forward-looking view on bringing differentiable programming into real-world computation.
Don’t forget to like, subscribe, and explore more talks from FerriteCon 2025 for cutting-edge developments in Julia and scientific computing!
#FerriteCon2025 #JuliaLang #DifferentiableProgramming #AutomaticDifferentiation #Enzyme #ScientificComputing
Join the channel to support the Julia Language project and access awesome perks!
youtube.com/channel/UC9IuUwwE2xdjQUT_LMLONoA/join
For more info on the Julia Programming Language, follow us on Twitter: twitter.com/JuliaLanguage and consider sponsoring us on GitHub: github.com/sponsors/JuliaLang
00:00 Welcome!
00:10 Help us add time stamps or captions to this video! See the description for details.
Want to help add timestamps to our YouTube videos to help with discoverability? Find out more here: github.com/JuliaCommunity/YouTubeVideoTimestamps
Interested in improving the auto generated captions? Get involved here: github.com/JuliaCommunity/YouTubeVideoSubtitles
In this insightful talk, Valentin Churavy (University of Augsburg) explores differentiable programming and how the Enzyme automatic differentiation framework brings powerful derivative capabilities to scientific computing workflows in Julia.
What this session covers:
• An introduction to how Enzyme enables differentiable programming by generating derivatives of complex scientific code patterns — even those involving mutation and control flow — directly from LLVM IR.
• Why differentiable programming is becoming essential in modern scientific computing, especially where gradients are needed for optimization, sensitivity analysis, and matrix-free methods.
• Demonstrations of how Enzyme integrates with Julia’s scientific ecosystem, empowering users to take derivatives of high-performance simulations without rewriting code.
Whether you’re into scientific simulations, automatic differentiation, or advanced Julia workflows, this talk gives a practical and forward-looking view on bringing differentiable programming into real-world computation.
Don’t forget to like, subscribe, and explore more talks from FerriteCon 2025 for cutting-edge developments in Julia and scientific computing!
#FerriteCon2025 #JuliaLang #DifferentiableProgramming #AutomaticDifferentiation #Enzyme #ScientificComputing
Join the channel to support the Julia Language project and access awesome perks!
youtube.com/channel/UC9IuUwwE2xdjQUT_LMLONoA/join
For more info on the Julia Programming Language, follow us on Twitter: twitter.com/JuliaLanguage and consider sponsoring us on GitHub: github.com/sponsors/JuliaLang
00:00 Welcome!
00:10 Help us add time stamps or captions to this video! See the description for details.
Want to help add timestamps to our YouTube videos to help with discoverability? Find out more here: github.com/JuliaCommunity/YouTubeVideoTimestamps
Interested in improving the auto generated captions? Get involved here: github.com/JuliaCommunity/YouTubeVideoSubtitles










