Hola,
¿eres nuevo aquí?

Regístrate gratis y conecta tu empresa con financiación pública, partners y proyectos.

Tengo cuenta

Regístrate

Ver video

SMILE

Financiado

Cerrado

Statistical Mechanics of Learning

"Computers are now able to recognize people, to tell a dog from a cat, or to process speech so efficiently that they can answer complicated questions. This was still impossible only a decade ago. This progress is largely due to th... ver más

28/02/2023

EPFL

1M€

Presupuesto del proyecto: 1M€

Líder del proyecto

ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE No se ha especificado una descripción o un objeto social para esta compañía.

TRL 4-5

Fecha límite participación Sin fecha límite de participación.

Ver 3 Participantes

Financiación concedida El organismo H2020 notifico la concesión del proyecto el día 2023-02-28

ERC-2016-STG: ERC Starting Grant

I+D

Cerrada hace 9 años

0% 100% 100%

Información adicional privada

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

3 Participantes

EPFL

599.75K€ | Lider

TOLSA

913.35K€ | Participante

CNRS

747.04K€ | Participante

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

Proyectos interesantes

QNets Open Quantum Neural Networks from Fundamental Concepts to I... 1M€ Cerrado

CNS2023-145392 Ciencias de la computación y tecnología informática 399K€ Cerrado

CoQHoNet Connecting Quantum Hopfield Networks 165K€ Cerrado

ALEPH Autonomous learning agents in Physics 184K€ Cerrado

QuantOrder Finding Order in Large scale Structures by Quantum Computing 140K€ Cerrado

PID2021-127781NB-I00 CARACTERIZACION ROBUSTA DE ESTADOS CUANTICOS 67K€ Cerrado

Duración del proyecto: 75 meses Fecha Inicio: 2016-11-16
Fecha Fin: 2023-02-28

Líder del proyecto

ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE No se ha especificado una descripción o un objeto social para esta compañía.

TRL 4-5

Presupuesto del proyecto 1M€

Fecha límite de participación Sin fecha límite de participación.

Descripción del proyecto "Computers are now able to recognize people, to tell a dog from a cat, or to process speech so efficiently that they can answer complicated questions. This was still impossible only a decade ago. This progress is largely due to the development of the artificial deep-learned neural networks. Nowadays, deep learning is revolutionizing our life, prompting an economic battle between internet giants and the creation of a myriad of start-ups. As attractive and performant as it is, however, many agree that deep learning is largely an empirical field that lacks a theoretical understanding of its capacity and limitations. The algorithms used to ""train"" these networks explore a very complex and non-convex energy landscape that eludes most of the present theoretical methodology in machine learning. The behavior of the dynamics in such complicated ""glassy"" landscape is, however, similar to those that have been studied for decades in the physics of disordered systems such as molecular and spin glasses. In this project we pursue this analogy and use advanced methods of disordered systems to develop a statistical mechanics approach to deep neural networks. Our first main objective is to create a model for learning features from data via a multi-level neural network. We then regard this model as a kind of a spin glass system amenable to an exact asymptotic analysis via the replica and cavity method. Analyzing its phase diagram and phase transitions shall bring theoretical understanding of the principles behind the empirical success of deep neural networks. This approach will also lead to our second objective: the creation of a new class of fast, efficient, and asymptotically optimal message passing algorithms for deep learning. It is the synergy between the theoretical statistical physics approach and scientific questions from computer science that makes the project’s objectives feasible and enables a leap forward in our understanding of learning from data. "

Conecta tu I+D

Entra hoy

¿Olvidé mi contraseña?

Financiación

Empresas

CTIs/Universidades

Proyectos

Investigadores