Zobrazeno 1 - 10
of 99
pro vyhledávání: '"OZAKI, ANA"'
Publikováno v:
Transactions on Graph Data and Knowledge, Vol 2, Iss 2, Pp 6:1-6:12 (2024)
We describe road data models which can represent high level features of a road network such as population, points of interest, and road length/cost and capacity, while abstracting from time and geographic location. Such abstraction allows for a simpl
Externí odkaz:
https://doaj.org/article/4dfbd92b57de4a07b13312a7350563d1
Publikováno v:
Transactions on Graph Data and Knowledge, Vol 2, Iss 3, Pp 2:1-2:29 (2024)
Ontology embedding methods are powerful approaches to represent and reason over structured knowledge in various domains. One advantage of ontology embeddings over knowledge graph embeddings is their ability to capture and impose an underlying schema
Externí odkaz:
https://doaj.org/article/487bb7e21ae243c7b282e2f8fd66fe08
Publikováno v:
Proceedings of the 33rd International Joint Conference on Artificial Intelligence (2024), pp.3567-3575
Labeled examples (i.e., positive and negative examples) are an attractive medium for communicating complex concepts. They are useful for deriving concept expressions (such as in concept learning, interactive concept specification, and concept refinem
Externí odkaz:
http://arxiv.org/abs/2412.17345
Decision trees are a popular machine learning method, known for their inherent explainability. In Explainable AI, decision trees can be used as surrogate models for complex black box AI models or as approximations of parts of such models. A key chall
Externí odkaz:
http://arxiv.org/abs/2412.10513
Research on knowledge graph embeddings has recently evolved into knowledge base embeddings, where the goal is not only to map facts into vector spaces but also constrain the models so that they take into account the relevant conceptual knowledge avai
Externí odkaz:
http://arxiv.org/abs/2408.04913
Autor:
Æsøy, Kristoffer, Ozaki, Ana
Machine learning models, and in particular language models, are being applied to various tasks that require reasoning. While such models are good at capturing patterns their ability to reason in a trustable and controlled manner is frequently questio
Externí odkaz:
http://arxiv.org/abs/2311.02765
We investigate semiring provenance--a successful framework originally defined in the relational database setting--for description logics. In this context, the ontology axioms are annotated with elements of a commutative semiring and these annotations
Externí odkaz:
http://arxiv.org/abs/2310.16472
Ontology embedding methods are powerful approaches to represent and reason over structured knowledge in various domains. One advantage of ontology embeddings over knowledge graph embeddings is their ability to capture and impose an underlying schema
Externí odkaz:
http://arxiv.org/abs/2310.02198
Modal logics are widely used in multi-agent systems to reason about actions, abilities, norms, or epistemic states. Combined with description logic languages, they are also a powerful tool to formalise modal aspects of ontology-based reasoning over a
Externí odkaz:
http://arxiv.org/abs/2307.12265
We investigate an approach for extracting knowledge from trained neural networks based on Angluin's exact learning model with membership and equivalence queries to an oracle. In this approach, the oracle is a trained neural network. We consider Anglu
Externí odkaz:
http://arxiv.org/abs/2305.12143