Hola,
¿eres nuevo aquí?

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

DeepLog

Financiado

Deep Probabilistic Logics

Neurosymbolic AI (NeSy) is the 3rd wave in AI. It wants to answer the key open question in AI as how to combine learning (2nd wave) and reasoning (1st wave) by integrating logic based AI with deep learning. However, there is only... ver más

31/10/2029

KU Leuven

3M€

Presupuesto del proyecto: 3M€

Líder del proyecto

KATHOLIEKE UNIVERSITEIT LEUVEN No se ha especificado una descripción o un objeto social para esta compañía.

TRL 4-5

Ver 1 Participantes

Financiación concedida El organismo HORIZON EUROPE notifico la concesión del proyecto el día 2024-05-16

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

ERC-2023-ADG: ERC ADVANCED GRANTS

I+D

Cerrada hace 1 año

0% 100%

1 Participantes

KU Leuven

2.50M€ | Lider

Proyectos interesantes

IJC2019-039152-I Deep Learning and Neural-symbolic learning and reasoning for... 93K€ Cerrado

BES-2017-080544 Cognitive and Intelligent Systems 93K€ Cerrado

IJC2019-039276-I Learning Symbolic Models for Generalized Planning in AI 93K€ Cerrado

INC10-0222 Sistemas Avanzados de Inteligencia 23K€ Cerrado

FJC2019-040479-I Knowledge acquisition for generalized planning 50K€ Cerrado

TIN2015-67959-P SOLUCIONADORES PARA LA INTELIGENCIA ARTIFICIAL GENERAL CON A... 82K€ Cerrado

Últimas noticias

27-11-2024: Videojuegos y creaci... Se abre la línea de ayuda pública: Ayudas para la promoción del sector del videojuego, del pódcast y otras formas de creación digital

27-11-2024: DGIPYME En las últimas 48 horas el Organismo DGIPYME ha otorgado 1 concesiones

27-11-2024: FUNDACION-EOI En las últimas 48 horas el Organismo FUNDACION EOI ha otorgado 2 concesiones

Duración del proyecto: 65 meses Fecha Inicio: 2024-05-16
Fecha Fin: 2029-10-31

Líder del proyecto

KATHOLIEKE UNIVERSITEIT LEUVEN

TRL 4-5

Presupuesto del proyecto 3M€

Descripción del proyecto Neurosymbolic AI (NeSy) is the 3rd wave in AI. It wants to answer the key open question in AI as how to combine learning (2nd wave) and reasoning (1st wave) by integrating logic based AI with deep learning. However, there is only little understanding of the underlying principles and there exist no widely used machine learning tools that support NeSy. This makes the development of learning and reasoning systems extremely hard. What is urgently needed is a paradigm shift in NeSy that focuses on foundations rather than on which system from the ‘alphabet-soup’ scores best on the latest benchmarks. I propose to develop these foundations by identifying key building blocks and demonstrate that they support the integration of knowledge and reasoning into any neural network learning task. My methodology is based on the slogan that I have coined: NeuroSymbolic AI = Neural + Probabilistic + Logical AI This advocates that we need to integrate the two main paradigms for reasoning (logic and probability), with that for learning (neural networks). I will exploit many similarities I have identified between statistical relational AI, which focuses on probabilistic logics, and NeSy. More specifically, I shall develop the foundations of NeSy. At the conceptual level, I shall identify the building blocks of NeSy by designing primitives that integrate logical, probabilistic and neural networks representations; at the semantic level, I shall introduce the notion of NeSy networks (that encompass logic circuits, algebraic operators and neural networks) as a semantic framework for NeSy; at the computational level, I will show how to exploit NeSy networks for inference and learning. DEEPLOG is not 'yet another NeSy system', but rather a fundamental and operational framework in which a wide variety of NeSy systems and applications can be cast and implemented. We will develop an open-source software environment, and evaluate DEEPLOG ’s generality and applicability.

Conecta tu I+D

Entra hoy

Financiación

Empresas

CTIs/Universidades

Proyectos

Investigadores