We use cookies on this site to help provide the best possible online experience. By using this site you agree to our use of cookies.
Click to view our cookie policy and customize your cookie preferences.
Online
The Algorithmic Differentiation (AD) world basically splits in two. Source transformation can give incredibly efficient adjoints, but is restricted to "simple languages" like subsets of C. On the other hand, operator overloading has successfully handled large production codes, but in general is less efficient than source transformation. But there's nothing stopping us combining these two ideas. It turns out that this is somewhat tricky to do, but by no means impossible.
In this webinar, Senior Technical Consultant, Viktor Mosenkis talks about this hybrid approach to Adjoint AD. This approach provides source transformation like performance whilst being as easy to apply as operator overloading.
This webinar will provide:
| Online
AI is reshaping UK higher education, and this panel led by Mary Curnock Cook CBE will explore how institutions can strategically adopt AI to enhance student outcomes while scaling responsibly.
| Online
This webinar will show how LearnWise AI in Moodle helps deliver scalable, personalized feedback while enhancing student engagement and supporting equitable assessment.
| Online
Join Jisc and Macrium for an introduction to their Back Up and Recovery products.
Join our mailing list for the latest news, event information and resources