Hola,
Are you new here?

I have an account

Conecta con

+150K Projects

+300K Companies

+230 Financiaciones

¿Te ayudamos?

Ejemplos de búsqueda

Vídeos Explicativos

DYNASTY

financed

Closed

Dynamics-Aware Theory of Deep Learning

The recent advances in deep learning (DL) have transformed many scientific domains and have had major impacts on industry and society. Despite their success, DL methods do not obey most of the wisdoms of statistical learning theor... see more

30/09/2027

INRIA

1M€

Project Budget: 1M€

Project leader

INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQU... No se ha especificado una descripción o un objeto social para esta compañía.

TRL 4-5

PARTICIPATION DEPralty Sin fecha límite de participación.

Financing granted El organismo HORIZON EUROPE notifico la concesión del proyecto The day 2022-06-03

ERC-2021-STG: ERC STARTING GRANTS Scope:Objectives

I+D

Cerrada

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.

1 Participantes

INRIA

1.50M€ | Leader

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: 63 months Date Start: 2022-06-03
End date: 2027-09-30

Project leader

INSTITUT NATIONAL DE RECHERCHE EN INFORMATIQU... No se ha especificado una descripción o un objeto social para esta compañía.

TRL 4-5

Project Budget 1M€

participation deadline Sin fecha límite de participación.

Project description The recent advances in deep learning (DL) have transformed many scientific domains and have had major impacts on industry and society. Despite their success, DL methods do not obey most of the wisdoms of statistical learning theory, and the vast majority of the current DL techniques mainly stand as poorly understood black-box algorithms. Even though DL theory has been a very active research field in the past few years, there is a significant gap between the current theory and practice: (i) the current theory often becomes vacuous for models with large number of parameters (which is typical in DL), and (ii) it cannot capture the interaction between data, architecture, training algorithm and its hyper-parameters, which can have drastic effects on the overall performance. Due to this lack of theoretical understanding, designing new DL systems has been dominantly performed by ad-hoc, 'trial-and-error' approaches. The main objective of this proposal is to develop a mathematically sound and practically relevant theory for DL, which will ultimately serve as the basis of a software library that provides practical tools for DL practitioners. In particular, (i) we will develop error bounds that closely reflect the true empirical performance, by explicitly incorporating the dynamics aspect of training, (ii) we will develop new model selection, training, and compression algorithms with reduced time/memory/storage complexity, by exploiting the developed theory. To achieve the expected breakthroughs, we will develop a novel theoretical framework, which will enable tight analysis of learning algorithms in the lens of dynamical systems theory. The outcomes will help relieve DL from being a black-box system and avoid the heuristic design process. We will produce comprehensive open-source software tools adapted to all popular DL libraries, and test the developed algorithms on a wide range of real applications arising in computer vision, audio/music/natural language processing.

Conecta tu I+D

Entra hoy

Forgot your password?

Financing

Companies

CTIs/Universidades

Projects

researchers

What is innovating.Works? Lose yourself in the best search engine for innovative companies you've ever seen, see how your competition is funded, connect with that partner you didn't know about, discover R&D projects that need you, and much, much more just a click away.

Smart Company-Financial Motor Innovating tiene un perfil tecnológico financiero de 400.000 empresas gracias al cual sabe a qué ayuda puede ir o no cualquier empresa de forma automática. Parece magia pero es tecnología.

Create your project and find partners ¿Tienes un proyecto y buscas un partner? Una Universidad, Centro Tecnológico, Consultoría? Este es tu sitio. Gracias al motor de búsqueda podemos recomendarte los mejores socios y ponerte en contacto con ellos.