Français
Statistical theory for deep neural networks - lecture 2
Virtualconference
Authors : Schmidt-Hieber, Johannes (Author of the conference)
CIRM (Publisher )
65Mxx - Numerical methods for IVP of PDE
68T07 - Artificial neural networks and deep learning
Additional resources :
http://smai.emath.fr/cemracs/cemracs21/data/presentation-speakers/hands-on-DNN.py
CIRM (Publisher )
Loading the player...
|
Abstract :
Recently a lot of progress has been made regarding the theoretical understanding of machine learning methods in particular deep learning. One of the very promising directions is the statistical approach, which interprets machine learning as a collection of statistical methods and builds on existing techniques in mathematical statistics to derive theoretical error bounds and to understand phenomena such as overparametrization. The lecture series surveys this field and describes future challenges.
MSC Codes : 65Mxx - Numerical methods for IVP of PDE
68T07 - Artificial neural networks and deep learning
Additional resources :
http://smai.emath.fr/cemracs/cemracs21/data/presentation-speakers/hands-on-DNN.py
|
Information on the Video
Film maker : Hennenfent, GuillaumeLanguage : English Available date : 16/08/2021 Conference Date : 23/07/2021 Subseries : Research School arXiv category : Statistics Theory ; Machine Learning Mathematical Area(s) : Probability & Statistics Format : MP4 (.mp4) - HD Video Time : 01:53:48 Targeted Audience : Researchers Download : https://videos.cirm-math.fr/2021-07-23-Schmidt-Hieber_2.mp4 
|
Information on the Event
Event Title : CEMRACS 2021: Data Assimilation and Model Reduction in High Dimensional Problems / CEMRACS 2021: Assimilation de données et réduction de modèle pour des problêmes en grande dimensionEvent Organizers : Ehrlacher, Virginie ; Lombardi, Damiano ; Mula Hernandez, Olga ; Nobile, Fabio ; Taddei, Tommaso Dates : 19/07/2021 - 23/07/2021 Event Year : 2021 Event URL : https://conferences.cirm-math.fr/2412.html
Citation Data
DOI : 10.24350/CIRM.V.19781603Cite this video as: Schmidt-Hieber, Johannes (2021). Statistical theory for deep neural networks - lecture 2. CIRM. Audiovisual resource. doi:10.24350/CIRM.V.19781603 URI : http://dx.doi.org/10.24350/CIRM.V.19781603 |
See Also
- [Multi angle] Bayesian data assimilation and filtering - lecture 2 / Author of the conference Schillings, Claudia.
- [Multi angle] Interatomic potentials from symmetry-adapted polynomial fits / Author of the conference Dusson, Geneviève.
- [Multi angle] How to compute transition times? / Author of the conference Lelièvre, Tony.
- [Multi angle] Coupling models instead of coupling codes: two toy examples / Author of the conference Lafitte, Olivier.
- [Virtualconference] Statistical theory for deep neural networks - lecture 1 / Author of the conference Schmidt-Hieber, Johannes.
- [Multi angle] High-dimensional optimization methods - lecture 2 / Author of the conference Moulines, Eric.
- [Multi angle] High-dimensional optimization methods - lecture 1 / Author of the conference Moulines, Eric.
- [Multi angle] Approximation and learning with tree tensor networks - lecture 2 / Author of the conference Nouy, Anthony.
- [Multi angle] Approximation and learning with tree tensor networks - lecture 1 / Author of the conference Nouy, Anthony.
- [Virtualconference] Bayesian methods for inverse problems - lecture 2 / Author of the conference Dashti, Masoumeh.
- [Multi angle] Theory of approximation of high-dimensional functions - lecture 2 / Author of the conference Cohen, Albert.
Bibliography
Imagette Video
