Auflistung nach:
Auflistung Künstliche Intelligenz 34(4) - Dezember 2020 nach Erscheinungsdatum
1 - 10 von 21
Treffer pro Seite
Sortieroptionen
- ZeitschriftenartikelInterview with Diego Calvanese(KI - Künstliche Intelligenz: Vol. 34, No. 4, 2020) Calvanese, Diego; Šimkus, Mantas
- ZeitschriftenartikelIn Memoriam Christian Freksa(KI - Künstliche Intelligenz: Vol. 34, No. 4, 2020) Piel, Helen; Seising, Rudolf
- ZeitschriftenartikelThe AAA ABox Abduction Solver(KI - Künstliche Intelligenz: Vol. 34, No. 4, 2020) Pukancová, Júlia; Homola, MartinAAA is a sound and complete ABox abduction solver based on the Reiter’s MHS algorithm and the Pellet reasoner. It supports DL expressivity up to $$\mathcal {SROIQ}$$ SROIQ (i.e., OWL 2). It supports multiple observations, and allows to specify abducibles.
- ZeitschriftenartikelOur Software Production is Still Some Sort of Hacking(KI - Künstliche Intelligenz: Vol. 34, No. 4, 2020) Visser, Ubbo
- ZeitschriftenartikelRewriting Approaches for Ontology-Mediated Query Answering(KI - Künstliche Intelligenz: Vol. 34, No. 4, 2020) Ahmetaj, ShqiponjaA most promising approach to answering queries in ontology-based data access (OBDA) is through query rewriting. In this paper we present novel rewriting approaches for several extensions of OBDA. The goal is to understand their relative expressiveness and to pave the way for efficient query answering algorithms.
- ZeitschriftenartikelData Access With Horn Ontologies: Where Description Logics Meet Existential Rules(KI - Künstliche Intelligenz: Vol. 34, No. 4, 2020) Mugnier, Marie-LaureTwo main families of ontology languages are considered in the context of data access, namely Horn description logics and existential rules. In this paper, we review the semantic relationships between these families in the light of the ontology-mediated query answering problem. To this end, we rely on the standard translation of description logics in first-order logic and on the notion of semantic emulation. We focus on description logics and classes of existential rules for which the conjunctive query answering problem has polynomial data complexity.
- ZeitschriftenartikelTowards Explanatory Interactive Image Captioning Using Top-Down and Bottom-Up Features, Beam Search and Re-ranking(KI - Künstliche Intelligenz: Vol. 34, No. 4, 2020) Biswas, Rajarshi; Barz, Michael; Sonntag, DanielImage captioning is a challenging multimodal task. Significant improvements could be obtained by deep learning. Yet, captions generated by humans are still considered better, which makes it an interesting application for interactive machine learning and explainable artificial intelligence methods. In this work, we aim at improving the performance and explainability of the state-of-the-art method Show, Attend and Tell by augmenting their attention mechanism using additional bottom-up features. We compute visual attention on the joint embedding space formed by the union of high-level features and the low-level features obtained from the object specific salient regions of the input image. We embed the content of bounding boxes from a pre-trained Mask R-CNN model. This delivers state-of-the-art performance, while it provides explanatory features. Further, we discuss how interactive model improvement can be realized through re-ranking caption candidates using beam search decoders and explanatory features. We show that interactive re-ranking of beam search candidates has the potential to outperform the state-of-the-art in image captioning.
- ZeitschriftenartikelVisual Landmarks are Exaggerated: A Theoretical and Empirical View on the Meaning of Landmarks in Human Wayfinding(KI - Künstliche Intelligenz: Vol. 34, No. 4, 2020) Hamburger, KaiAre landmarks exaggerated in human wayfinding? Daniel R. Montello says yes, and I basically agree with his opinion. However, I do agree on a different level. My aim for this discussion article is to point out why landmarks are indeed exaggerated in this research context and I will try to approach this claim from several perspectives. First, the research focus in this field is, unfortunately, mainly on visual landmarks. Second, other modalities than vision—e.g., auditory and/or olfactory senses—can be used for landmark-based wayfinding. Third, we need to clearly differentiate between conscious/effortful and unconscious/automatic processing of spatial information in the context of landmark-based wayfinding. Finally, I will suggest that landmarks, even if exaggerated in the visual domain, are (still) of significant importance in human wayfinding and spatial cognition.
- ZeitschriftenartikelRethinking Computer Science Through AI(KI - Künstliche Intelligenz: Vol. 34, No. 4, 2020) Kersting, Kristian
- ZeitschriftenartikelNews(KI - Künstliche Intelligenz: Vol. 34, No. 4, 2020)
- «
- 1 (current)
- 2
- 3
- »