RM+ML: 20. Asymptotic Eigenvalue Distribution in the Random Feature Model

Описание к видео RM+ML: 20. Asymptotic Eigenvalue Distribution in the Random Feature Model

The lecture notes for the course can be found at https://rolandspeicher.com/wp-content...
neural network, random features, non-linear random matrix theory

0:00 Recap of random feature model
7:50 Theorem on asymptotic eigenvalue distribution
23:22 Special cases of theorem
34:15 General form of the result

The goal of this lecture series is to cover mathematical interesting aspects of neural networks, in particular, those related to random matrices. In this 20th lecture we state the theorem on the asymptotic eigenvalue distribution in the random feature model, look on some special cases and point out that the effect of the non-linearity is to add an independent noise to the linear model.

Комментарии

Информация по комментариям в разработке

Похожие видео