Hola,
¿eres nuevo aquí?

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

Tengo cuenta

Regístrate

Ver video

A-B-C-Deep

Financiado

Algorithmic Bias Control in Deep learning

"Deep Learning (DL) has reached unparalleled performance in many domains. However, this impressive performance typically comes at the cost of gathering large datasets and training massive models, requiring extended time and prohib... ver más

31/05/2027

TECHNION ISRAEL I...

2M€

Presupuesto del proyecto: 2M€

Líder del proyecto

TECHNION ISRAEL INSTITUTE OF TECHNOLOGY 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 2022-05-17

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

I+D

Cerrada hace 3 años

0% 100% 100%

Información adicional privada

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

1 Participantes

TECHNION ISRAEL INSTITUTE O...

1.50M€ | 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

REAL Reliable and cost effective large scale machine learning 1M€ Cerrado

FastML FastML: Efficient and Cost-Effective Distributed Machine Lea... 150K€ Cerrado

PID2021-128045OA-I00 APRENDIZAJE PROFUNDO ETICO 56K€ Cerrado

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

DeepLearning 2.0 DeepLearning 2.0: Meta-Learning Qualitatively New Components 2M€ Cerrado

PID2019-110051GB-I00 POLITICAS Y MECANISMOS ARQUITECTURALES PARA LA MEJORA DE REN... 36K€ Cerrado

Duración del proyecto: 60 meses Fecha Inicio: 2022-05-17
Fecha Fin: 2027-05-31

Líder del proyecto

TECHNION ISRAEL INSTITUTE OF TECHNOLOGY 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 (DL) has reached unparalleled performance in many domains. However, this impressive performance typically comes at the cost of gathering large datasets and training massive models, requiring extended time and prohibitive costs. Significant research efforts are being invested in improving DL training efficiency, i.e., the amount of time, data, and resources required to train these models, by changing the model (e.g., architecture, numerical precision) or the training algorithm (e.g., parallelization). Other modifications aim to address critical issues, such as credibility and over-confidence, which hinder the implementation of DL in the real world. However, such modifications often cause an unexplained degradation in the generalization performance of DL to unseen data. Recent findings suggest that this degradation is caused by changes to the hidden algorithmic bias of the training algorithm and model. This bias selects a specific solution from all solutions which fit the data. After years of trial-and-error, this bias in DL is often at a ""sweet spot"" which implicitly allows ANNs to learn well, due to unknown key design choices. But performance typically degrades when these choices change. Therefore, understanding and controlling algorithmic bias is the key to unlocking the true potential of deep learning. Our goal is to develop a rigorous theory of algorithmic bias in DL and to apply it to alleviate critical practical bottlenecks that prevent such models from scaling up or implemented in real-world applications. Our approach has three objectives: (1) identify the algorithmic biases affecting DL; (2) understand how these biases affect the functional capabilities and generalization performance; and (3) control these biases to alleviate critical practical bottlenecks. To demonstrate the feasibility of this challenging project, we describe how recent advances and concrete preliminary results enable us to effectively approach all these objectives."

Conecta tu I+D

Entra hoy

¿Olvidé mi contraseña?

Financiación

Empresas

CTIs/Universidades

Proyectos

Investigadores