Zobrazeno 1 - 10
of 114
pro vyhledávání: '"Ken Kaneiwa"'
Autor:
Yuga Oishi, Ken Kaneiwa
Publikováno v:
IEEE Access, Vol 11, Pp 34421-34430 (2023)
Various graph neural networks (GNNs) have been proposed to solve node classification tasks in machine learning for graph data. GNNs use the structural information of graph data by aggregating the feature vectors of neighboring nodes. However, they fa
Externí odkaz:
https://doaj.org/article/fdc202ade285479aa6ef7883af1808aa
Autor:
Yuga Oishi, Ken Kaneiwa
Publikováno v:
IEEE Access, Vol 11, Pp 16974-16983 (2023)
Node classification on graph data is a major problem in machine learning, and various graph neural networks (GNNs) have been proposed. Variants of GNNs such as H2GCN and CPF outperform graph convolutional networks (GCNs) by improving on the weaknesse
Externí odkaz:
https://doaj.org/article/15756bfb50f44e03aab45802674dd665
Autor:
Takuma Nagai, Ken Kaneiwa
Publikováno v:
Transactions of the Japanese Society for Artificial Intelligence. 35:B-J62_1
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::654839cbfc28384470741049c1155f18
https://doi.org/10.1527/tjsai.b-j62
https://doi.org/10.1527/tjsai.b-j62
Autor:
Philip H. P. Nguyen, Ken Kaneiwa
Publikováno v:
Applied Artificial Intelligence. 28:139-177
□ This article proposes a method to perform automated inference from event assertions through the use of an ontology formalized under Conceptual Structure Theory. An upper event ontology is first presented as an example of how the ontology is built
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::37b7e56f02b5ed4f71363d91953209f7
https://doi.org/10.1080/08839514.2014.875682
https://doi.org/10.1080/08839514.2014.875682
Autor:
Ken Kaneiwa, Koji Fujiwara
Publikováno v:
Transactions of the Japanese Society for Artificial Intelligence. 29:364-374
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::41da00d939f8c834f772e09d1ba9428b
https://doi.org/10.1527/tjsai.29.364
https://doi.org/10.1527/tjsai.29.364
Autor:
Ken Kaneiwa, Takuma Nagai
Publikováno v:
Transactions of the Japanese Society for Artificial Intelligence. 29:343-355
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::020a9170139e2e758b998392061d283c
https://doi.org/10.1527/tjsai.29.343
https://doi.org/10.1527/tjsai.29.343
Autor:
Ken Kaneiwa, Norihiro Kamide
Publikováno v:
Fundamenta Informaticae. 125:51-70
A logic called sequence-indexed linear logic SLL is proposed to appropriately formalize resource-sensitive reasoning with sequential information. The completeness and cut-elimination theorems for SLL are proved, and SLL and a fragment of SLL are show
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4dfdc43ac6dec46f4eaf7ab3d30e4809
https://doi.org/10.3233/fi-2013-852
https://doi.org/10.3233/fi-2013-852
Autor:
Ken Kaneiwa, Philip H. P. Nguyen
Publikováno v:
Knowledge and Information Systems. 35:463-492
This paper presents a decidable order-sorted query system for reasoning between ontologies and rules. We describe order-sorted logic programming with sort, predicate, and meta-predicate hierarchies (OSL3h), which derives predicate and meta-predicate
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::317315cfd0309515cf1212a4d7b3c7ff
https://doi.org/10.1007/s10115-012-0513-x
https://doi.org/10.1007/s10115-012-0513-x
Autor:
Ken Kaneiwa, Norihiro Kamide
Publikováno v:
New Generation Computing. 29:391-408
It is known that paraconsistent logical systems are more appropriate for inconsistency-tolerant and uncertainty reasoning than other types of logical systems. In this paper, a paraconsistent computation tree logic, PCTL, is obtained by adding paracon
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f6982cc7a21e57563618d67d6f98b037
https://doi.org/10.1007/s00354-009-0116-6
https://doi.org/10.1007/s00354-009-0116-6
Autor:
Ken Kaneiwa
Publikováno v:
Knowledge-Based Systems. 24:629-641
Order-sorted logic is a useful tool for knowledge representation and reasoning because it enables representation of sorted terms and formulas along with partially ordered sorts (called sort-hierarchy). However, this logic cannot represent more comple
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e0f42668d61e7135802e5071e490e0be
https://doi.org/10.1016/j.knosys.2011.02.001
https://doi.org/10.1016/j.knosys.2011.02.001