Hola,
¿eres nuevo aquí?

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

Tengo cuenta

Regístrate

Ver video

CoDeFeL

Financiado

Control for Deep and Federated Learning

Machine Learning (ML) is forging a new era in Applied Mathematics (AM), leading to innovative and powerful methods. But the need for theoretical guarantees generates challenging, fundamental, deep mathematical questions. This gre... ver más

31/08/2029

FAU

2M€

Presupuesto del proyecto: 2M€

Líder del proyecto

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

TRL 4-5

Ver 2 Participantes

Financiación concedida El organismo HORIZON EUROPE notifico la concesión del proyecto el día 2023-10-10

ERC-2022-ADG: ERC ADVANCED GRANTS Scope:Objectives

I+D

Cerrada hace 2 años

0% 100% 100%

2 Participantes

FAU

2.50M€ | Lider

DEUSTO

1.31M€ | 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

PID2020-120087GB-C21 NUEVO METODO DE APRENDIZAJE POR REFUERZO MULTIOBJETIVO BASAD... 54K€ Cerrado

FJC2020-043823-I Desarollo de modelos personalizados de Federated Learning Cerrado

CORaL Correlations-Oriented Representation Learning 173K€ Cerrado

TIN2008-06242 TRANFERENCIA INDIRECTA DE POLITICAS EN APRENDIZAJE RELACIONA... 24K€ Cerrado

TUCLA Theoretical Understanding of Classic Learning Algorithms 2M€ Cerrado

APHELEIA Reconciling Classical and Modern (Deep) Machine Learning for... 2M€ Cerrado

Duración del proyecto: 70 meses Fecha Inicio: 2023-10-10
Fecha Fin: 2029-08-31

Líder del proyecto

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

TRL 4-5

Presupuesto del proyecto 2M€

Descripción del proyecto Machine Learning (ML) is forging a new era in Applied Mathematics (AM), leading to innovative and powerful methods. But the need for theoretical guarantees generates challenging, fundamental, deep mathematical questions. This great challenge can be addressed from the perspective of other, more mature areas of AM. CoDeFeL seeks to do so from the rich interface between Control Theory (CT) and ML, contributing to the analytical foundations of ML methods, significantly enlarging, and updating the range of applications of CT. As our recent results show, classification, regression, and prediction problems in Supervised Learning (SL) and the Universal Approximation Theorem can be successfully recast as the simultaneous or ensemble controllability property of Residual Neural Networks (ResNets). Following this path, we will develop ResNets of minimal complexity and cost, addressing the deep, intricate issue of linking the structure of the data set to be classified with the dynamics of the networks trained. Taking the turnpike principle as our inspiration, we will build new simplified ResNet architectures. This, however, raises major challenges for the genuinely nonlinear dynamics that ResNets represent.Adjoint methods will also be developed and applied, to understand the sensitivity of ResNets, and proposing techniques for Adversarial Training and computing Saliency Maps, applicable in Unsupervised Learning. The project is strongly inspired on the challenges arising in relevant applications in digital medicine and internet recommendation systems, among other areas. Accordingly, we will also develop a body of rich, hybrid, cutting-edge methods for data-aware modelling, combining ResNet surrogate models and those inspired on Mechanics, with the aid of Model Predictive Control strategies. New Federated Learning methodologies with privacy preservation guarantees will also be developed. The computational counterparts will be brought together in a new CoDeFeL GitHub repository.

Conecta tu I+D

Entra hoy

¿Olvidó su contraseña?

Financiación

Empresas

CTIs/Universidades

Proyectos

Investigadores