Hola,
¿eres nuevo aquí?

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

Tengo cuenta

Regístrate

Ver video

DeepLearning 2.0

Financiado

DeepLearning 2.0: Meta-Learning Qualitatively New Components

Deep learning has revolutionized many fields, such as computer vision, speech recognition, natural language processing, and reinforcement learning. This success is based on replacing domain-specific hand-cra... ver más

30/04/2027

ALU-FR

2M€

Presupuesto del proyecto: 2M€

Líder del proyecto

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

TRL 4-5

Financiación concedida El organismo HORIZON EUROPE notifico la concesión del proyecto el día 2022-04-14

ERC-2021-COG: ERC CONSOLIDATOR GRANTS Scope:Objectives

I+D

Cerrada hace 3 años

0% 100% 100%

1 Participantes

ALU-FR

2.00M€ | Lider

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

RTI2018-102285-A-I00 APRENDIZAJE PROFUNDO MULTIMODAL ESTRUCTURADO 28K€ Cerrado

PTQ2018-009909 OPTIMIZACIÓN DE HIPER-PARÁMETROS Y ARQUITECTURAS EN MODELOS... 115K€ Cerrado

PID2020-117142GB-I00 APRENDIZAJE PROFUNDO EFICIENTE PARA SECUENCIAS DE VIDEO Y NU... 117K€ Cerrado

Rand4TrustPool Random sampling for trustworthy pooling layers in graph neur... 227K€ Cerrado

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

BeyondBlackbox Data Driven Methods for Modelling and Optimizing the Empiric... 1M€ Cerrado

Duración del proyecto: 60 meses Fecha Inicio: 2022-04-14
Fecha Fin: 2027-04-30

Líder del proyecto

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

TRL 4-5

Presupuesto del proyecto 2M€

Descripción del proyecto Deep learning has revolutionized many fields, such as computer vision, speech recognition, natural language processing, and reinforcement learning. This success is based on replacing domain-specific hand-crafted features with features that are learned for the particular task at hand. The logical step to take deep learning to the next level is to also (meta-)learn other hand-crafted elements of the deep learning pipeline. We therefore propose to develop meta-level learning methods for the creation of novel customized deep learning pipelines, by means of: 1. Hierarchical neural architecture searchfor learning qualitatively new architectures and architectural building blocks from scratch; 2. Learning of optimizers and hyperparameter adaptation policies that adapt totheir context in order to converge faster and more robustly; 3. Learning the data to train on, to remove the need for large sets of labelled data; and 4. Bootstrapping from prior design efforts to increase efficiency and make an integrative design of architectures, optimizers, hyperparameter adaptation policies, and pretraining tasks feasible in practice. These advances will allow the next generation of deep learning pipelines to achieve higher accuracy, lower training time, and improved ease-of-use (democratization of deeplearning). They will also allow a customization to particular design contexts, including additional objectives next to accuracy (such as robustness, memory requirements, energy consumption, latency, interpretability, training cost, uncertainty estimation, and algorithmic fairness) in order to facilitate trustworthy AI. In order to demonstrate the effectiveness of these methods, we plan to develop: 5. New state-of-the-art customized deep learning pipelines for various applications, including EEG decoding, RNA folding, and improving the reinforcement learning pipeline and deep learning on tabular data.

Conecta tu I+D

Entra hoy

¿Olvidé mi contraseña?

Financiación

Empresas

CTIs/Universidades

Proyectos

Investigadores