Kernels for deep learning - with and without tricks∗

Abstract

Neural networks have recently re-emerged as a powerful hypothesis class, yielding impressive empirical performance in multiple domains. However, their training is a non-convex optimization problem which poses exciting theoretical and practical challenges. Here we argue that by extending the class of neural nets, one can obtain a convex learning problem… (More)
View Slides

Topics

Figures and Tables

Sorry, we couldn't extract any figures or tables for this paper.

Slides referencing similar topics