10,843 Hits in 4.5 sec

Special issue on semantic deep learning

Dagmar Gromann, Luis Espinosa Anke, Thierry Declerck, Pascal Hitzler, Krzysztof Janowicz
2019 Semantic Web Journal  
Bridging the neural-symbolic gap by joining deep learning and Semantic Web not only holds the potential of improving performance but also of opening up new avenues of research.  ...  This editorial introduces the Semantic Web Journal special issue on Semantic Deep Learning, which brings together Semantic Web and deep learning research.  ...  Acknowledgements We would like to thank all the authors of accepted and rejected articles for their efforts and the editorsin-chief of Semantic Web Journal, Pascal Hitzler and Krzysztof Janowicz, for their  ... 
doi:10.3233/sw-190364 fatcat:hnmi2xowhvdvdheagxuzlnmqmu

Reports of the AAAI 2012 Conference Workshops

Vikas Agrawal, Jorge Baier, Kostas Bekris, Yiling Chen, Artur S. D'Avila Garcez, Pascal Hitzler, Patrik Haslum, Dietmar Jannach, Edith Law, Freddy Lecue, Luis C. Lamb, Cynthia Matuszek (+7 others)
2012 The AI Magazine  
, Human Computation, Intelligent Techniques for Web Personalization and Recommendation, Multiagent Pathfinding, Neural-Symbolic Learning and Reasoning, Problem Solving Using Classical Planners, Semantic  ...  The AAAI-12 Workshop program was held Sunday and Monday, July 22–23, 2012 at the Sheraton Centre Toronto Hotel in Toronto, Ontario, Canada.  ...  Lokendra Shastri heads the Enterprise Technology Research Labs and the Center for Knowledge Driven Intelligent Systems at Infosys Limited.  ... 
doi:10.1609/aimag.v33i4.2444 fatcat:2q2x223h6vhzda342ifqbhtwlq

Predicting Strategic Behavior from Free Text (Extended Abstract)

Omer Ben-Porat, Lital Kuchy, Sharon Hirsch, Guy Elad, Roi Reichart, Moshe Tennenholtz
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
The connection between messaging and action is fundamental both to web applications, such as web search and sentiment analysis, and to economics.  ...  This paper aims to connect these two strands of research, which we consider highly timely and important due to the vast online textual communication on the web.  ...  That is especially true for the field of neural-symbolic computation (NeSy) [Besold et al., 2017; , where the goal is to integrate symbolic reasoning and neural networks.  ... 
doi:10.24963/ijcai.2020/688 dblp:conf/ijcai/RaedtDMM20 fatcat:kbp4p2slsrculnqg2ig2dvchde

Reports on the 2013 AAAI Fall Symposium Series

Gully Burns, Yolanda Gil, Yan Liu, Natalia Villanueva-Rosales, Sebastian Risi, Joel Lehman, Jeff Clune, Christian Lebiere, Paul S. Rosenbloom, Frank Van Harmelen, James A. Hendler, Pascal Hitzler (+2 others)
2014 The AI Magazine  
(FS-13-02); Integrated Cognition (FS-13-03); Semantics for Big Data (FS-13-04); and Social Networks and Social Contagion: Web Analytics and Computational Social Science (FS-13-05).  ...  , Artificial Neural Networks, or — ?  ...  explored the many opportunities and challenges arising from transferring and adapting semantic web technologies to the big data quest.  ... 
doi:10.1609/aimag.v35i2.2538 fatcat:sg6wyb2r7na7pmfticcrapdvca

Knowledge graph using resource description framework and connectionist theory

Ravi Lourdusamy, Xavierlal J Mattam
2020 Journal of Physics, Conference Series  
The weighted RDF in Graph Neural Network will represent the knowledge graph using RDF and connectionist theory.  ...  This article presents the use of weighted RDF as a vector embedding of RDF that could be used with Bayesian networks in Graph Neural Networks.  ...  The term and the structure were later used to refer to semantic web knowledge bases [20] .  ... 
doi:10.1088/1742-6596/1427/1/012001 fatcat:uqnd3tliczdhtarlu256inzjtu

Machine Learning Meets the Semantic Web

Konstantinos Ilias Kotis, Konstantina Zachila, Evaggelos Paparidis
2021 Artificial Intelligence Advances  
This paper presents how Machine Learning (ML) meets the Semantic Web and how KGs are related to Neural Networks and Deep Learning.  ...  The emerging Graph Neural Networks (GNN) can extract both object characteristics and relations from KGs.  ...  The symbol-based category consists of methods that aim to tackle the Semantic Web problem from the viewpoint of reasoning.  ... 
doi:10.30564/aia.v3i1.3178 fatcat:vq47pxxmkja2blzz4gaterau7q

Deep Algorithmic Question Answering: Towards a Compositionally Hybrid AI for Algorithmic Reasoning [article]

Kwabena Nuamah
2021 arXiv   pre-print
We argue that the challenge of algorithmic reasoning in QA can be effectively tackled with a "systems" approach to AI which features a hybrid use of symbolic and sub-symbolic methods including deep neural  ...  Additionally, we argue that while neural network models with end-to-end training pipelines perform well in narrow applications such as image classification and language modelling, they cannot, on their  ...  Acknowledgment The author would like to thank Vaishak Belle, Alan Bundy and Thomas Fletcher for feedback on an earlier draft and Huawei for supporting the research on which this paper was based under grant  ... 
arXiv:2109.08006v3 fatcat:35ugb3qfdvg2djua7tvh4asll4

Patient and Graph Embeddings for Predictive Diagnosis of Drug Iatrogenesis [chapter]

Lina F. Soualmia, Vincent Lafon, Stéfan J. Darmoni
2021 Studies in Health Technology and Informatics  
as models founded on transformers, and symbolic artificial intelligence.  ...  The documents' embeddings, the graphs' embeddings of biomedical concepts, and patients' embeddings, all of them semantically enriched with aligned formal ontologies and semantic networks, will constitute  ...  It will combine machine learning, deep neural networks trained on heterogenous data sources, such as drug databases, scientific and grey literature, and real-life data, but also symbolic and semantic reasoning  ... 
doi:10.3233/shti210205 pmid:34042611 fatcat:u4vjos5nbnc4bkweuy3yuohflm

Explaining Trained Neural Networks with Semantic Web Technologies: First Steps [article]

Md Kamruzzaman Sarker, Ning Xie, Derek Doran, Michael Raymer, Pascal Hitzler
2017 arXiv   pre-print
We apply existing Semantic Web technologies in order to provide an experimental proof of concept.  ...  The ever increasing prevalence of publicly available structured data on the World Wide Web enables new applications in a variety of domains.  ...  This work was supported by the Ohio Federal Research Network project Human-Centered Big Data.  ... 
arXiv:1710.04324v1 fatcat:nasjjyx3engn3pp62l6llmmebe

A Short Review of Symbol Grounding in Robotic and Intelligent Systems

Silvia Coradeschi, Amy Loutfi, Britta Wrede
2013 Künstliche Intelligenz  
The focus is in the use of symbol grounding for robotics and intelligent system.  ...  The review covers a number of subtopics, that include, physical symbol grounding, social symbol grounding, symbol grounding for vision systems, anchoring in robotic systems, and learning symbol grounding  ...  Acknowledgements We would like to thank Tony Belpaeme, Fredrik Heintz, Sven Albrecht, Angelo Cangelosi, Paul Vogt, Katerina Pastra and Sverin Lemaignan for their helpful comments to improve the article  ... 
doi:10.1007/s13218-013-0247-2 fatcat:ghimcniy6na3fk7yqf54typjiu

Interoperability and machine-to-machine translation model with mappings to machine learning tasks [article]

Jacob Nilsson and Fredrik Sandin and Jerker Delsing
2019 arXiv   pre-print
Modern large-scale automation systems integrate thousands to hundreds of thousands of physical sensors and actuators.  ...  We present alternative mathematical definitions of the translator learning task and mappings to similar machine learning tasks and solutions based on recent developments in machine learning.  ...  Concepts and methods developed for the semantic web [17] are widely used to integrate human-and machine-readable metadata to support the adapter engineering and system integration processes, such as  ... 
arXiv:1903.10735v1 fatcat:v7e7nghfnja25chbrx5xdnfjme

The semantic method for agents' knowledge representation in the Cognitive Integrated Management Information System

Marcin Hernes
2015 Position Papers of the 2015 Federated Conference on Computer Science and Information Systems  
This paper presents a method for agents' knowledge representation by using semantic network with node and links activation level defined on the instance, concept, relation and axiom level.  ...  The first part shortly presents the state-of-the-art in the considered field; next, the CIMIS prototype is shortly characterized; the formal definition of a method for agents' knowledge representation  ...  The main of them include first-order predicate logic, production systems, artificial neural networks, frame representation, ontologies such as semantic web, semantic networks and topic maps, multi-attributes  ... 
doi:10.15439/2015f319 dblp:conf/fedcsis/Hernes15 fatcat:ezg6pnr6yrc33nv2hz5zlescyq

Logic-Based Technologies for Intelligent Systems: State of the Art and Perspectives

Roberta Calegari, Giovanni Ciatto, Enrico Denti, Andrea Omicini
2020 Information  
Together with the disruptive development of modern sub-symbolic approaches to artificial intelligence (AI), symbolic approaches to classical AI are re-gaining momentum, as more and more researchers exploit  ...  Since logic-based approaches lay at the core of symbolic AI, summarizing their state of the art is of paramount importance now more than ever, in order to identify trends, benefits, key features, gaps,  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/info11030167 fatcat:e3wed54dyzabldrnml7khx37te

Combinations of case-based reasoning with other intelligent methods

Jim Prentzas, Ioannis Hatzilygeroudis, Ioannis Hatzilygeroudis, Constantinos Koutsojannis
2009 International Journal of Hybrid Intelligent Systems  
Whenever a new case has to be dealt with, the most similar cases are retrieved from the case base and their encompassed knowledge is exploited in the current situation.  ...  We illustrate basic types of such combinations and discuss future directions.  ...  Intelligent Decision Support Systems in the semantic Web framework should be able to handle, integrate with and reason from distributed data and information on the Web [3] .  ... 
doi:10.3233/his-2009-0096 fatcat:xfryblu7k5debo4ndmsmh6aep4

A Proposal for Common Dataset in Neural-Symbolic Reasoning Studies

Özgür Yilmaz, Artur S. d'Avila Garcez, Daniel L. Silver
2016 International Workshop on Neural-Symbolic Learning and Reasoning  
We promote and analyze the needs of a common publicly available benchmark dataset to be used for neural-symbolic studies of learning and reasoning.  ...  Along with the original tasks that were suggested by the Visual Genome creators, we propose neural-symbolic tasks that can be used as challenges to promote research in the field and competition between  ...  We would like to thank the reviewers for detailed and very beneficial comments on the paper.  ... 
dblp:conf/nesy/YilmazGS16 fatcat:qf3grff5nbbjdbszeihh5ugghy
« Previous Showing results 1 — 15 out of 10,843 results