Zobrazeno 1 - 10
of 576
pro vyhledávání: '"De Raedt, Luc"'
Recent developments in AI have reinvigorated pursuits to advance the (life) sciences using AI techniques, thereby creating a renewed opportunity to bridge different fields and find synergies. Headlines for AI and the life sciences have been dominated
Externí odkaz:
http://arxiv.org/abs/2410.13487
Neural probabilistic logic systems follow the neuro-symbolic (NeSy) paradigm by combining the perceptive and learning capabilities of neural networks with the robustness of probabilistic logic. Learning corresponds to likelihood optimization of the n
Externí odkaz:
http://arxiv.org/abs/2408.08133
Large Language Models (LLMs) are said to possess advanced reasoning abilities. However, some skepticism exists as recent works show how LLMs often bypass true reasoning using shortcuts. Current methods for assessing the reasoning abilities of LLMs ty
Externí odkaz:
http://arxiv.org/abs/2408.07215
The limitations of purely neural learning have sparked an interest in probabilistic neurosymbolic models, which combine neural networks with probabilistic logical reasoning. As these neurosymbolic models are trained with gradient descent, we study th
Externí odkaz:
http://arxiv.org/abs/2406.04472
The integration of learning and reasoning is high on the research agenda in AI. Nevertheless, there is only a little attention to use existing background knowledge for reasoning about partially observed scenes to answer questions about the scene. Yet
Externí odkaz:
http://arxiv.org/abs/2403.03203
Publikováno v:
International Journal of Approximate Reasoning (2024): 109130
The field of probabilistic logic programming (PLP) focuses on integrating probabilistic models into programming languages based on logic. Over the past 30 years, numerous languages and frameworks have been developed for modeling, inference and learni
Externí odkaz:
http://arxiv.org/abs/2402.13782
Large Language Models (LLMs) have demonstrated impressive planning abilities due to their vast "world knowledge". Yet, obtaining plans that are both feasible (grounded in affordances) and cost-effective (in plan length), remains a challenge, despite
Externí odkaz:
http://arxiv.org/abs/2308.12682
Autor:
Hazra, Rishi, De Raedt, Luc
Despite numerous successes in Deep Reinforcement Learning (DRL), the learned policies are not interpretable. Moreover, since DRL does not exploit symbolic relational representations, it has difficulties in coping with structural changes in its enviro
Externí odkaz:
http://arxiv.org/abs/2304.08349
Argumentation problems are concerned with determining the acceptability of a set of arguments from their relational structure. When the available information is uncertain, probabilistic argumentation frameworks provide modelling tools to account for
Externí odkaz:
http://arxiv.org/abs/2304.00879
Autor:
De Smet, Lennert, Martires, Pedro Zuidberg Dos, Manhaeve, Robin, Marra, Giuseppe, Kimmig, Angelika, De Raedt, Luc
Neural-symbolic AI (NeSy) allows neural networks to exploit symbolic background knowledge in the form of logic. It has been shown to aid learning in the limited data regime and to facilitate inference on out-of-distribution data. Probabilistic NeSy f
Externí odkaz:
http://arxiv.org/abs/2303.04660