Hola,
¿eres nuevo aquí?

Registrate y conecta tu empresa con financiación pública, partners y proyectos.

NoKnow

Financiado

Not Knowing in Deep Representation Learning

Machine learning and artificial intelligence techniques are progressing at a tremendous pace and impressive results appear across scientific fields. However, as machine learning models grow in capacity, they become increasingly ‘b... ver más

31/07/2029

TECHNICAL UNIVERSI...

2M€

Presupuesto del proyecto: 2M€

Líder del proyecto

DANMARKS TEKNISKE UNIVERSITET 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 2024-04-12

Línea de financiación objetivo El proyecto se financió a través de la siguiente ayuda:

ERC-2023-COG: ERC CONSOLIDATOR GRANTS

I+D

Cerrada hace 1 año

0% 100% 100%

1 Participantes

TECHNICAL UNIVERSITY OF DENM...

2.00M€ | Lider

Proyectos interesantes

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

IJC2018-036205-I Métodos de aprendizaje profundo que modelizan la incertidumb... 93K€ Cerrado

MTM2014-55262-P PROBLEMAS ALGORITMICOS Y DE COMPLEJIDAD EN APRENDIZAJE AUTOM... 35K€ Cerrado

Understanding DL Understanding Deep Learning 1M€ Cerrado

EIN2020-112480 DEL MODELO MATEMATICO A LA DECISION HUMANA: POSICIONANDO A E... 9K€ Cerrado

PRE2020-092608 APRENDIZAJE AUTOMATICO ESCALABLE Y EXPLICABLE 99K€ Cerrado

Últimas noticias

01-12-2024: REDES En las últimas 48 horas el Organismo REDES ha otorgado 1337 concesiones

01-12-2024: IDAE En las últimas 48 horas el Organismo IDAE ha otorgado 4 concesiones

01-12-2024: AEI En las últimas 48 horas el Organismo AEI ha otorgado 23 concesiones

Duración del proyecto: 63 meses Fecha Inicio: 2024-04-12
Fecha Fin: 2029-07-31

Líder del proyecto

DANMARKS TEKNISKE UNIVERSITET

TRL 4-5

Presupuesto del proyecto 2M€

Descripción del proyecto Machine learning and artificial intelligence techniques are progressing at a tremendous pace and impressive results appear across scientific fields. However, as machine learning models grow in capacity, they become increasingly ‘black box’, and it becomes harder for humans to reason about the patterns discovered by the machine. A root cause of this difficulty is that most machine learning models can express the same pattern in infinitely many, equally good, ways within their internal representations of the world. This is known as an identifiability problem. Today we lack a general solution to identifiability problems, and either give up on understanding the patterns discovered by the machine or reduce model complexity to lessen the problem. The latter also reduces the fidelity and applicability of the model. NoKnow rephrase the question of identifiability to be concerned with tasks solved by the representation rather than the representation itself. Using tools from differential geometry and Bayesian inference, we develop the theoretical tools to ensure that tasks solved in the representation have an identifiable outcome even if the representations themselves are not identifiable. To turn theory into practice, we develop state-of-the-art algorithms for assessing the uncertainty of learned representations in order to indirectly estimate the topology of the representation manifold. We further develop novel, high-fidelity predictive models that have identifiable outcomes when trained on learned representations. NoKnow provides the fundamental tools needed to engage with learned representations to guarantee identifiable outcomes. This, in turn, increase trust in findings as they are not dependent on arbitrariness in learned representations. As society increasingly automates decisions, this trust in machine learning becomes ever more important.

Conecta tu I+D

Entra hoy

Financiación

Empresas

CTIs/Universidades

Proyectos

Investigadores