View, browse and sort the ever-growing list of sessions by pass type, topic, and format. With this Session Scheduler, you can build your schedule in advance and access it during the show via export or with the GDC Mobile App, once live. Sessions do fill up so please arrive early to sessions that you would like to attend. Adding a session to your schedule does not guarantee you a seat.
Daniel Holden (Animation Researcher, Ubisoft Montreal)
Pass Type: All Access Pass, Core+Summits Pass, Core Pass - Get your pass now!
Vault Recording: TBD
We know Machine Learning is a powerful tool to tackle problems we can't solve by conventional means, but what about things we already have solutions for, such as physics simulations? Is there any reason to use Machine Learning in these cases? It turns out there is because in some cases Machine Learning allows us to trade-off computation time in exchange for additional memory usage, which can often be used to provide massive performance gains at runtime. In this talk I will show how we used Neural Networks and vast amounts of training data to construct extremely fast approximations of interactive physics and cloth simulations which achieved around 300 to 5000 times speedup over standard simulations, opening up new opportunities for what is possible within typical physics simulation budgets.
Attendees will gain an understanding of how Machine Learning and Neural Networks can be applied to physics simulations, as well as why and how it can make sense to apply Machine Learning to problems we already can solve via conventional means.
This session is accessible for game developers of any experience and should be particularly interesting to physics, graphics, and animation programmers who want to know in a bit more depth when and why Machine Learning can provide a performance boost to their problems.