Online Program Home
My Program

Abstract Details

Activity Number: 625 - Modern Non-Parametrics
Type: Invited
Date/Time: Thursday, August 1, 2019 : 10:30 AM to 12:20 PM
Sponsor: IMS
Abstract #300200 Presentation
Title: Statistical Risk Bounds for Deep Neural Networks
Author(s): Johannes Schmidt-Hieber*
Companies: Leiden University
Keywords: Neural networks; Estimation; Rates of convergence; Deep learning
Abstract:

Recently, deep neural networks have been successfully trained to achieve impressive results for complicated tasks such as object detection on images and speech recognition. In the talk we provide an overview of the field and describe new bounds for the statistical estimation risk of deep neural networks.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2019 program