Hola,
Are you new here?

STRUDEL

financed

Information Theory beyond Communications Distributed Representations and Deep L...

Information Theory beyond Communications Distributed Representations and Deep Learning 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... see more

31/08/2020

CENTRALESUPELEC

171K€

Project Budget: 171K€

Project leader

CENTRALESUPELEC No se ha especificado una descripción o un objeto social para esta compañía.

TRL 4-5

PARTICIPATION DEPralty Sin fecha límite de participación.

Ver 3 Participantes

Financing granted El organismo H2020 notifico la concesión del proyecto The day 2020-08-31

MSCA-IF-2017: Individual Fellowships Objective:The goal of the Individual Fellowships is to enhance the creative and innovative potential...

I+D

Cerrada does 7 years

0% 100% 100%

characteristics of the participant

Este proyecto no cuenta con búsquedas de partenariado abiertas en este momento.

Private Information

No hay información privada compartida para este proyecto. Habla con el coordinador.

3 Participantes

CENTRALESUPELEC

171.35K€ | Leader

UNIVERSITE DE MONTREAL

UDEM

78.81K€ | participant

Conecta tu I+D

¿Tienes un proyecto y buscas un partner? Gracias a nuestro motor inteligente podemos recomendarte los mejores socios y ponerte en contacto con ellos. Te lo explicamos en este video

Project duration: 28 months Date Start: 2018-04-05
End date: 2020-08-31

Project leader

CENTRALESUPELEC No se ha especificado una descripción o un objeto social para esta compañía.

TRL 4-5

Project Budget 171K€

participation deadline Sin fecha límite de participación.

Project description 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

Conecta tu I+D

Entra hoy

Forgot your password?

Financing

Companies

CTIs/Universidades

Projects

researchers