Opendata, web and dolomites

STRUDEL SIGNED

Information Theory beyond Communications: Distributed Representations and Deep Learning

Total Cost €

0

EC-Contrib. €

0

Partnership

0

Views

0

 STRUDEL project word cloud

Explore the words cloud of the STRUDEL project. It provides you a very rough idea of what is the project "STRUDEL" about.

good    solidly    framework    statistics    collaborative    record    nets    supervisor    network    model    serve    autoencoders    accomplishing    workpackages    criteria    individual    collaborating    reconstruction    fellow    started    input    breaking    learning    complexity    successful    split    inputs    statistical    labels    ae    multilayer    mathematical    algorithms    extracting    performance    powerful    bottleneck    relationship    idea    codes    2017    gap    fertile    aes    appear    backgrounds    researcher    convert    dimensional    endeavor    he    building    capitalize    deep    hence    innovation    theory    power    variety    grounded    thorough    lia    lab    paradigm    machine    goals    architectures    generative    cnrs    representation    trained    neural    theoretic    networks    adversarial    representations    basic    complementary    variables    innovative    stochastic    transfer    hidden    block    tradeoffs    bridge    tc    structured    free    intimate    explanations    motivated    enormously    descriptive    expertise   

Project "STRUDEL" data sheet

The following table provides information about the project.

Coordinator
CENTRALESUPELEC 

Organization address
address: PLATEAU DE MOULON 3 RUE JOLIOT CURIE
city: GIF SUR YVETTE
postcode: 91192
website: n.a.

contact info
title: n.a.
name: n.a.
surname: n.a.
function: n.a.
email: n.a.
telephone: n.a.
fax: n.a.

 Coordinator Country France [FR]
 Total cost 171˙349 €
 EC max contribution 171˙349 € (100%)
 Programme 1. H2020-EU.1.3.2. (Nurturing excellence by means of cross-border and cross-sector mobility)
 Code Call H2020-MSCA-IF-2017
 Funding Scheme MSCA-IF-GF
 Starting year 2018
 Duration (year-month-day) from 2018-09-01   to  2020-08-31

 Partnership

Take a look of project's partnership.

# participants  country  role  EC contrib. [€] 
1    CENTRALESUPELEC FR (GIF SUR YVETTE) coordinator 171˙349.00
2    UNIVERSITE DE MONTREAL CA (MONTREAL) partner 0.00

Map

Leaflet | Map data © OpenStreetMap contributors, CC-BY-SA, Imagery © Mapbox

 Project objective

Deep learning is an enormously successful recent paradigm with record-breaking performance in numerous applications. Individual autoencoders (AEs) of a multilayer neural network are trained to convert high-dimensional inputs into low-dimensional codes that allow the reconstruction of the input. Although some explanations appear to be solidly grounded, there is no mathematical understanding of the AE learning process. This project is a collaborative endeavor of researchers with strong complementary backgrounds. Its main innovation is the idea to capitalize on powerful and fertile concepts from information theory (expertise of researcher) in order to advance the state of the art in deep learning (expertise of supervisor at TC). The innovative research work is motivated by our recent insight that there is an intimate relationship between AEs, generative adversarial nets and the information bottleneck method. This method is a model-free approach for extracting information from observed variables that are relevant to hidden representations or labels and will serve as basic building block for an information theory of representation learning. The planned objectives are split into 3 workpackages: 1) information-theoretic criteria and statistical tradeoffs for extracting good representations, 2) structured architectures/algorithms for learning, 3) use of stochastic complexity to assess the descriptive power (model selection) of deep neural networks. Accomplishing the challenging goals of this proposal requires a variety of methodologies with a rich potential for transfer of knowledge between the involved fields of information theory, statistics and machine learning. Our new framework is expected to bridge the gap between theory and practice to facilitate a more thorough understanding and hence improved design of deep learning architectures. The fellow researcher is coordinating the LIA Lab of the CNRS (started in 2017) where he is collaborating with the supervisor at TC

Are you the coordinator (or a participant) of this project? Plaese send me more information about the "STRUDEL" 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 "STRUDEL" are provided by the European Opendata Portal: CORDIS opendata.

More projects from the same programme (H2020-EU.1.3.2.)

RealFlex (2019)

Real-time simulator-driver design and manufacturing based on flexible systems

Read More  

ToMComputations (2019)

How other minds are represented in the human brain: Neural computations underlying Theory of Mind

Read More  

TheaTheor (2018)

Theorizing the Production of 'Comedia Nueva': The Process of Play Configuration in Spanish Golden Age Theater

Read More