Neural Network Learns The Physics of Fluids and Smoke | Two Minute Papers #118
Channel:Two Minute Papers · Length:5:26 · Published:2017-01-08 · Views:208771
Summary
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.
Why HN recommends it
It is cited as an early example of neural networks learning physics, and recalled during later discussions of AI video generation.
Machine learning & deep learning · Computer graphics & rendering
Subtitles (excerpt)
Dear Fellow Scholars, this is Two Minute Papers with Károly Zsolnai-Fehér. This piece of work is still in progress done by one of the members of the Google Brain research team and several researchers from the amazing New York University. The goal was to show a neural network video footage of lots and lots of fluid and smoke simulations, and have it learn how the dynamics work, to the point that it can continue and guess how the behavior of a smoke puff would change in time. We stop the video and it would learn how to continue it, if you will. Now that is a tall order if I've ever seen one. Most of this episode will not be about the technical details of this method, but about the importance and ramifications of such a technique. And since almost all the time, our episodes are about already published works, it also makes a great case study on how to evaluate and think about the merits and shortcomings of a research project that is still in the works. This definitely is an interesting take as normally, we use neural networks to solve problems that are otherwise close to impossible to tackle. Here, the neural networks are applied to solve something that we already know how to solve. And the question immediately comes to mind, why would anyone bother to do that?
On Hacker News
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 - [VIDEO] — visarga, 2017-01
That reminds me of an episode of '2 Minute Papers' I saw 7 years ago, covering research to that effect: [VIDEO] — Fricken, 2024-07
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 … — sitkack, 2018-01
Related videos
- RL Course by David Silver - Lecture 1: Introduction to Reinforcement Learning · Google DeepMind · 1:28:12
- Why Greatness Cannot Be Planned — Kenneth Stanley · Machine Learning Street Talk · 2:46:27
- High-Speed Robot Hand · Hizook · 3:00
- Attention Is All You Need · Yannic Kilcher · 27:06
- RAAIS 2017 - Simon Knowles, Co-Founder and CTO of Graphcore · The Research and Applied AI Summit - RAAIS · 35:44
- The spelled-out intro to neural networks and backpropagation: building micrograd · Andrej Karpathy · 2:25:52
- But what is a neural network? | Deep learning chapter 1 · 3Blue1Brown · 18:40
- The Beauty of Bézier Curves · Freya Holmér · 24:25
- The Continuity of Splines · Freya Holmér · 1:13:50
- elevated by Rgba & TBC | 4k intro (FullHD 1080p demoscene demo) · Demoscene High-Quality Videos (Annikras) · 3:36
- AlphaGo - The Movie | Full award-winning documentary · Google DeepMind · 1:30:28
- Transformers, the tech behind LLMs | Deep Learning Chapter 5 · 3Blue1Brown · 27:14
- Painting a Character with Maths · Inigo Quilez · 24:46
- USENIX Security '18-Q: Why Do Keynote Speakers Keep Suggesting That Improving Security Is Possible? · USENIX · 51:22
- The Real Story Behind Wayland and X - Daniel Stone (linux.conf.au 2013) · Mladen Mijatov · 45:35
- Lecture 1 | Machine Learning (Stanford) · Stanford · 1:08:40