DLT SIGNED
Deep Learning Theory: Geometric Analysis of Capacity, Optimization, and Generalization for Improving Learning in Deep Neural Networks
Total Cost €
0EC-Contrib. €
0Partnership
0Views
0DLT project word cloud
Explore the words cloud of the DLT project. It provides you a very rough idea of what is the project "DLT" about.
Project "DLT" data sheet
The following table provides information about the project.
| Coordinator |
MAX-PLANCK-GESELLSCHAFT ZUR FORDERUNG DER WISSENSCHAFTEN EV
Organization address contact info |
| Coordinator Country | Germany [DE] |
| Total cost | 1˙500˙000 € |
| EC max contribution | 1˙500˙000 € (100%) |
| Programme |
1. H2020-EU.1.1. (EXCELLENT SCIENCE - European Research Council (ERC)) |
| Code Call | ERC-2017-STG |
| Funding Scheme | ERC-STG |
| Starting year | 2018 |
| Duration (year-month-day) | from 2018-07-01 to 2023-06-30 |
Partnership
Take a look of project's partnership.
| # | ||||
|---|---|---|---|---|
| 1 | MAX-PLANCK-GESELLSCHAFT ZUR FORDERUNG DER WISSENSCHAFTEN EV | DE (Munich) | coordinator | 1˙500˙000.00 |
Map
Project objective
Deep Learning is one of the most vibrant areas of contemporary machine learning and one of the most promising approaches to Artificial Intelligence. Deep Learning drives the latest systems for image, text, and audio processing, as well as an increasing number of new technologies. The goal of this project is to advance on key open problems in Deep Learning, specifically regarding the capacity, optimization, and regularization of these algorithms. The idea is to consolidate a theoretical basis that allows us to pin down the inner workings of the present success of Deep Learning and make it more widely applicable, in particular in situations with limited data and challenging problems in reinforcement learning. The approach is based on the geometry of neural networks and exploits innovative mathematics, drawing on information geometry and algebraic statistics. This is a quite timely and unique proposal which holds promise to vastly streamline the progress of Deep Learning into new frontiers.
Publications
| year | authors and title | journal | last update |
|---|---|---|---|
| 2018 |
Lin, Alex Tong ; Li, Wuchen ; Osher, Stanley and Montúfar, Guido Wasserstein proximal of GANs published pages: , ISSN: , DOI: |
2020-04-01 | |
| 2018 |
Wuchen Li, Guido Montúfar Natural gradient via optimal transport published pages: 181-214, ISSN: 2511-2481, DOI: 10.1007/s41884-018-0015-3 |
Information Geometry 1/2 | 2020-04-01 |
| 2019 |
Ay, Nihat ; Rauh, Johannes and Montúfar, Guido A continuity result for optimal memoryless planning in POMDPs published pages: , ISSN: , DOI: |
2020-04-01 | |
| 2019 |
Lin, Alex Tong ; Dukler, Yonatan ; Li, Wuchen and Montúfar, Guido Wasserstein diffusion Tikhonov regularization. Optimal Transport and Machine Learning published pages: , ISSN: , DOI: |
2020-04-01 | |
| 2019 |
Dukler, Yonatan ; Li, Wuchen ; Lin, Alex Tong and Montúfar, Guido Wasserstein of Wasserstein loss for learning generative models published pages: , ISSN: , DOI: |
Proceedings of the 36th international conference on machine learning, 9-15 June 2019, Long Beach, California, USA | 2020-04-01 |
Are you the coordinator (or a participant) of this project? Plaese send me more information about the "DLT" project.
For instance: the website url (it has not provided by EU-opendata yet), the logo, a more detailed description of the project (in plain text as a rtf file or a word file), some pictures (as picture files, not embedded into any word file), twitter account, linkedin page, etc.
Send me an email (fabio@fabiodisconzi.com) and I put them in your project's page as son as possible.
Thanks. And then put a link of this page into your project's website.
The information about "DLT" are provided by the European Opendata Portal: CORDIS opendata.