Title:
Lecture 4: Mathematics for Deep Neural Networks: Statistical theory for deep ReLU networks
Lecture 4: Mathematics for Deep Neural Networks: Statistical theory for deep ReLU networks
dc.contributor.author | Schmidt-Hieber, Johannes | |
dc.contributor.corporatename | Georgia Institute of Technology. Transdisciplinary Research Institute for Advancing Data Science | en_US |
dc.contributor.corporatename | University of Twente. Dept. of Applied Mathematics | en_US |
dc.date.accessioned | 2019-03-28T18:00:58Z | |
dc.date.available | 2019-03-28T18:00:58Z | |
dc.date.issued | 2019-03-15 | |
dc.description | Presented on March 15, 2019 at 10:30 a.m. in the Groseclose Building, Room 402. | en_US |
dc.description | Johannes Schmidt-Hieber is the Chair of Statistics in the Department of Applied Mathematics at the University of Twente. His research topics include statistical theory for deep neural networks, nonparametric Bayes, confidence statements for qualitative constraints, asymptotic equivalence, and spot volatility estimation. | en_US |
dc.description | Runtime: 58:39 minutes | en_US |
dc.description.abstract | We outline the theory underlying the recent bounds on the estimation risk of deep ReLU networks. In the lecture, we discuss specific properties of the ReLU activation function that relate to skipping connections and efficient approximation of polynomials. Based on this, we show how risk bounds can be obtained for sparsely connected networks. | en_US |
dc.format.extent | 58:39 minutes | |
dc.identifier.uri | http://hdl.handle.net/1853/60957 | |
dc.language.iso | en_US | en_US |
dc.relation.ispartofseries | TRIAD Distinguished Lecture Series | en_US |
dc.subject | Deep neural networks | en_US |
dc.subject | Kolmogorov-Arnold | en_US |
dc.subject | Localization | en_US |
dc.title | Lecture 4: Mathematics for Deep Neural Networks: Statistical theory for deep ReLU networks | en_US |
dc.type | Moving Image | |
dc.type.genre | Lecture | |
dspace.entity.type | Publication | |
local.contributor.corporatename | Transdisciplinary Research Institute for Advancing Data Science | |
local.relation.ispartofseries | Transdisciplinary Research Institute for Advancing Data Science Lectures | |
relation.isOrgUnitOfPublication | 09be376c-3b5f-4fa8-9e58-6a3595a8353b | |
relation.isSeriesOfPublication | f402db73-162f-4a58-a9d2-bc56b6a0af52 |
Files
Original bundle
1 - 4 of 4
No Thumbnail Available
- Name:
- schmidt-hieber4.mp4
- Size:
- 471.1 MB
- Format:
- MP4 Video file
- Description:
- Download video
No Thumbnail Available
- Name:
- schmidt-hieber4_videostream.html
- Size:
- 1.01 KB
- Format:
- Hypertext Markup Language
- Description:
- Streaming video
No Thumbnail Available
- Name:
- transcript.txt
- Size:
- 45.36 KB
- Format:
- Plain Text
- Description:
- Transcription
- Name:
- thumbnail.jpg
- Size:
- 120.44 KB
- Format:
- Joint Photographic Experts Group/JPEG File Interchange Format (JFIF)
- Description:
- Thumbnail
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 3.13 KB
- Format:
- Item-specific license agreed upon to submission
- Description: