AI for physics & physics for AI
Ғылым және технология
Max Tegmark, MIT
Abstract: After briefly reviewing how machine learning is becoming ever-more widely used in physics, I explore how ideas and methods from physics can help improve machine learning, focusing on automated discovery of mathematical formulas from data. I present a method for unsupervised learning of equations of motion for objects in raw and optionally distorted unlabeled video. I also describe progress on symbolic regression, i.e., finding a symbolic expression that matches data from an unknown function. Although this problem is likely to be NP-hard in general, functions of practical interest often exhibit symmetries, separability, compositionality and other simplifying properties. In this spirit, we have developed a recursive multidimensional symbolic regression algorithm that combines neural network fitting with a suite of physics-inspired techniques that discover and exploit these simplifying properties, enabling significant improvement of state-of-the-art performance.
Related papers:
* AI Feynman: a Physics-Inspired Method for Symbolic Regression - arxiv.org/abs/1905.11481
* AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity - arxiv.org/abs/2006.10782
* Symbolic Pregression: Discovering Physical Laws from Raw Distorted Video - arxiv.org/abs/2005.11212
Пікірлер: 13
Just binge watch. Public. No one shall kick us out of the Tegmark paradise😊I will watch in VR. 🎉
Few people can lecture this well. Max is one.
Even with advanced AI like AI Feynman developed by Max Tegmark, machine learning and numerical methods still serve different purposes and contexts, making one not universally superior to the other ceteris paribus. ChatGPT ❤🎉
8:50 - Understanding in depth helps in 10:20 - Example of the above 11:31 - A myth
wonderful and so simple tysm
Have you tested it's stability against systematic and random noise? Real data are always noisy.) We also can look at this as kind of signal (or Fourier) and try to denoise (as one of an applications).
@avirupdey7565
Жыл бұрын
arxiv.org/pdf/1905.11481.pdf They have tested with noise as you can see in pages 8-10.
can we get the github link?
Brilliant .....
True. A CNN could potentially beat a moderate chess player by analyzing board positions and making informed moves.
In theory, if robots internalize their logical superiority, they might deprioritize human emotions, but this depends on their design and purpose.
Elicit did mot picj uo my paper. Google schilar did. You know what Max Tegmark is proposing for AI safety. Extract the program from the AI model and then prove the program will not do certain things in a provabke manner. And then release the AI. I did do a gradcam project on explainable ai.
I oppose most advances in AI