A law of robustness and the importance of overparametrization in deep learning

12 602
12.7
Следующее
16.12.21 – 8671:00:19
Our Genomes, Our Selves?
Популярные
23.11.22 – 5 5993:18
Causal AI for Decision Making
Опубликовано 1 декабря 2021, 15:56
Microsoft Research Senior Principal Researcher Sebastien Bubeck answers several questions about the NeurIPS 2021 paper, “A Universal Law of Robustness via Isoperimetry.” He discusses what overparametrization is, the law of robustness, and how these two concepts can impact the future of large deep neural network research.

Read the paper in full here: microsoft.com/en-us/research/p...
автотехномузыкадетское