Neural Network Learns The Physics of Fluids and Smoke | Two Minute Papers #118 on HackerTube: recommended by 1 Hacker News commenter across 1 month, 2017–2024.
explainer · dated
Two Minute Papers covers a paper on speeding up fluid and smoke simulation with convolutional networks. It contrasts the approach with earlier regression forest methods.
It is cited as an early example of neural networks learning physics, and recalled during later discussions of AI video generation.
3 Hacker News comments link this video. Each one links back to its thread.
Take a look at an application of deep learning in accelerating complex 3d rendering. (Two Minute Papers) Stunning Video Game Graphics With Voxel Cone Tracing - ▶ this video
in “Mathematicians bring ocean to life for Disney's 'Moana'” · View on HN
That reminds me of an episode of '2 Minute Papers' I saw 7 years ago, covering research to that effect: ▶ this video
in “New Sora Demo from OpenAI [video]” · View on HN
Linear Logic is amazing-ly useful, [link] Rust [0] wouldn't exist without it. Oddly enough, I think the next discontinuity in programming language design will be in making it easier to construct anytime [1], incremental [2] and succinct [3] programs. There is a tyranny of poor tolerancing that we currently have a very hard time from escaping. Is it that differentiable programs can be made sloppy in a way that a non-differentiable one can't? Have you looked at the research of using DNN for physics simulations? [4] [0] [link] [1] [link] [2] [link] [3] [link] [4] ▶ this video
in “Linear logic and deep learning [pdf]” · View on HN