Theoretical Physics for Machine Learning
Aspen Center For Physics
January 13-18, 2019
The AI revolution is here! Dramatic progress in machine learning, largely spurred by deep neural networks, has blown away benchmarks and solved problems decades earlier than expected. Despite this success, there remains much to learn about the principles governing these models. This Aspen Winter Conference will bring together researchers from the theoretical physics and artificial intelligence communities to discuss the physics of machine learning, with an eye towards both improved performance and progress on new challenges. The conference will investigate whether the tools and methodology of theoretical physics, formulated to describe the physical world, can be applied to understand the models and learning algorithms used in artificial intelligence. We hope that the conference will catalyze increased interaction between the theoretical physics and artificial intelligence communities.
Please check back for talk schedule and further information.
For questions, please contact us.
Scientific Organizing Committee
Adam Brown, Stanford University *
Ethan Dyer, Stanford University & Johns Hopkins *
Paul Ginsparg, Cornell University
Guy Gur-Ari, Institute for Advanced Study *
Jaehoon Lee, Google Brain
* Current affiliation: Google LLC
We thank our sponsors for supporting the conference.