@AnimaAnandkumar: A crucial ingredient missing from most AI models: the ability to understand the physical world. The best way to gain th…

A crucial ingredient missing from most AI models: the ability to understand the physical world. The best way to gain that understanding is to learn the continuous functions, the underlying mathematical relationships, that fully describe those systems. But many AI models were created for language processing or computer vision, where data can be treated as collections of isolated points, such as words in a sentence or a fixed set of pixels in an image. Instead, we propose a Neural Operator framework that shows how to extend existing neural network architectures in a way that allows AI systems to learn continuous functions. We take popular architectures like convolutional neural nets, transforms, graph neural nets and extend them to Neural Operators in a principled way. Thank you @Caltech for covering our work appearing in @Nature https://caltech.edu/about/news/extending-ai-architectures-to-address-continuous-scientific-problems… @mliuschi @JeanKossaifi @julberner