Filters








4,311 Hits in 7.4 sec

Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases [article]

Michael van Bekkum, Maaike de Boer, Frank van Harmelen, André Meyer-Vitali, Annette ten Teije
2021 arXiv   pre-print
, organised in a set of elementary patterns and a set of compositional patterns; 3) an application of these design patterns in two realistic use-cases for hybrid AI systems.  ...  In this paper we analyse a large body of recent literature and we propose a set of modular design patterns for such hybrid, neuro-symbolic systems.  ...  for Scientific Research NWO, https://hybrid-intelligence-centre.nl.  ... 
arXiv:2102.11965v2 fatcat:uo5wj6gw2vc6dhgdrdt26wqslq

Modular design patterns for hybrid learning and reasoning systems

Michael van Bekkum, Maaike de Boer, Frank van Harmelen, André Meyer-Vitali, Annette ten Teije
2021 Applied intelligence (Boston)  
organized in a set of elementary patterns and a set of compositional patterns; 3) an application of these design patterns in two realistic use-cases for hybrid AI systems.  ...  In this paper, we analyze a large body of recent literature and we propose a set of modular design patterns for such hybrid, neuro-symbolic systems.  ...  In this paper, we propose a set of modular design patterns for Hybrid AI systems that combine learning and reasoning (using combinations of data-driven and knowledge-driven AI components).  ... 
doi:10.1007/s10489-021-02394-3 fatcat:ecyruntfdncsbbtdglhllwc6vi

Modular Design Patterns for Hybrid Actors [article]

André Meyer-Vitali, Wico Mulder, Maaike H.T. de Boer
2021 arXiv   pre-print
Recently, a boxology (graphical language) with design patterns for hybrid AI was proposed, combining symbolic and sub-symbolic learning and reasoning.  ...  The main contributions of this paper are: 1) an extension of the taxonomy to describe distributed hybrid AI systems with actors and interactions; and 2) showing examples using a few design patterns relevant  ...  Consequently, it supports the design of hybrid AI systems using many different interaction, learning and reasoning patterns.  ... 
arXiv:2109.09331v2 fatcat:54j4qmgzevauzhkrlrteqfwwnm

A hybrid ontology-based information extraction system

Fernando Gutierrez, Dejing Dou, Stephen Fickas, Daya Wimalasuriya, Hui Zong
2016 Journal of information science  
Because the implementation strategy for the extraction of a concept is independent of the functionality of the extraction, we can design a hybrid OBIE system with concepts utilizing different implementation  ...  With this in mind, we have proposed a hybrid OBIE system, which incorporates both extraction rules and machine learning-based information extractors.  ...  without a combination strategy (1ML-3ER, 2ML-2ER, and 3ML-1ER), and multiple implementations with our proposed combination strategies (MinError and StackNB).  ... 
doi:10.1177/0165551515610989 fatcat:bnfhhmvsrza7tjowbemd6r4fem

A survey of multiple classifier systems as hybrid systems

Michał Woźniak, Manuel Graña, Emilio Corchado
2014 Information Fusion  
A current focus of intense research in pattern classification is the combination of several classifier systems, which can be built following either the same or different models and/or datasets building  ...  This paper presents an up-todate survey on multiple classifier system (MCS) from the point of view of Hybrid Intelligent Systems.  ...  Acknowledgments We would like to thank the anonymous reviewers for their diligent work and efficient efforts. We are also grateful to the Editorin-Chief, Prof. Belur V.  ... 
doi:10.1016/j.inffus.2013.04.006 fatcat:4pps7i2g2rbxpci7wjkqy2pska

Multiclassifier Systems: Back to the Future [chapter]

Joydeep Ghosh
2002 Lecture Notes in Computer Science  
This article argues that our current understanding of ensemble-type multiclassifier systems is now quite mature and exhorts the reader to consider a broader set of models and situations for further progress  ...  Some of these scenarios have already been considered in classical pattern recognition literature, but revisiting them often leads to new insights and progress.  ...  Modular learning systems are based on the precept that learning a large number of simple local concepts is both easier and more useful than learning a single complex global concept.  ... 
doi:10.1007/3-540-45428-4_1 fatcat:7aw5m7xakbcd3it23d4ckymxji

A Framework for Taxonomy and Evaluation of Self-Reconfigurable Robotic Systems

Ning Tan, Abdullah A. Hayat, Mohan R. Elara, Kristin L. Wood
2020 IEEE Access  
In this paper, we put forward a framework for taxonomy and evaluation (TAEV) of self-reconfigurable robots, based on the mechanism reconfigurability and the level of autonomy for reconfiguration.  ...  Self-reconfigurable robots have been proposed for a quite long period and in large numbers.  ...  Karthikeyan Elangovan and Mr. Thein Then Tun for discussion and giving valuable suggestions. (Ning Tan and Abdullah Aamir Hayat contributed equally to this work.)  ... 
doi:10.1109/access.2020.2965327 fatcat:zl53wznrvrap7k76bulcsfjakq

Foundations of Explainable Knowledge-Enabled Systems [article]

Shruthi Chari, Daniel M. Gruen, Oshani Seneviratne, Deborah L. McGuinness
2020 arXiv   pre-print
With the proliferation of AI-enabled systems in sometimes critical settings, there is a need for them to be explainable to end-users and decision-makers.  ...  We present a historical overview of explainable artificial intelligence systems, with a focus on knowledge-enabled systems, spanning the expert systems, cognitive assistants, semantic applications, and  ...  We thank our colleagues from IBM Research, Amar Das, Morgan Foreman and Ching-Hua Chen, and from RPI, James P. McCusker, and Rebecca Cowan, who greatly assisted the research and document preparation.  ... 
arXiv:2003.07520v1 fatcat:pz54e4ag35hf3osr7dfbmhb4ze

A Security Threats Taxonomy for Routing System Intrusion Detection

Fu Miao, Zhenxing Wang, Yi Guo, Liancheng Zhang
2016 2016 12th International Conference on Computational Intelligence and Security (CIS)  
This manuscript aims to provide researchers with a taxonomy and survey of current dataset composition and current Intrusion Detection Systems (IDS) capabilities and assets.  ...  To this end, this manuscript also provides a taxonomy and survey or network threats and associated tools.  ...  A Taxonomy and Survey of Intrusion Detection System Design Techniques, Network Threats and Datasets :9 A Taxonomy and Survey of Intrusion Detection System Design Techniques, Network Threats  ... 
doi:10.1109/cis.2016.0068 dblp:conf/cis/MiaoWGZ16 fatcat:qp7rz34u3fbhhlvfxl5nakdewe

Knowledge management tutorial: an editorial overview

A. Satyadas, U. Harigopal, N.P. Cassaigne
2001 IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)  
We present a tutorial on knowledge management (KM) and a roadmap of this special issue around the knowledge life cycle.  ...  Knowledge management is a discipline that provides strategy, process, and technology to share and leverage information and expertise that will increase our level of understanding, to more effectively solve  ...  Singh for motivating them to co-edit this special issue on knowledge management.  ... 
doi:10.1109/5326.983926 fatcat:4bycs2qg4jekbpqgo6nk5lz7nu

Morphees+

Hyunyoung Kim, Celine Coutrix, Anne Roudaut
2018 Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems - CHI '18  
For this reason, everyday reconfigurable objects have informed the design and taxonomy of shape changing UI. However, they have never been explored systematically.  ...  This paper analyses two established taxonomies -Rasmussen's and Roudaut's -using daily reconfigurable objects. We show relationships between the taxonomies and area for improvements.  ...  As a consequence, we use the term Morphees for the taxonomy features.  ... 
doi:10.1145/3173574.3174193 dblp:conf/chi/KimCR18a fatcat:i3emmzkhirdtvgkfcitbhlpdfu

A Consolidated System for Robust Multi-Document Entity Risk Extraction and Taxonomy Augmentation [article]

Berk Ekmekci, Eleanor Hagerman, Blake Howald
2019 arXiv   pre-print
We provide an overview of the system and expert evaluations for a range of token distances.  ...  Our system represents a more simplified architecture compared to alerting focused systems - motivated by high coverage use cases in the risk mining space such as due diligence activities and intelligence  ...  Acknowledgments Thank you to anonymous reviewers from NAACL Industry Track as well as Matt Machado, Nathan Maynes, and Scott McFadden for support and feedback.  ... 
arXiv:1909.10368v1 fatcat:55x3yz2zifafhlf56rzyt7dr64

Autonomous IoT Device Management Systems: Structured Review and Generalized Cognitive Model

Anders Eivind Braten, Frank Alexander Kraemer, David Palma
2020 IEEE Internet of Things Journal  
Data extracted from 32 relevant cases is first organized and analyzed according to a synthesized taxonomy of observed adaptation mechanisms, and then combined with state-of-the-art models of autonomous  ...  Based on our findings we substantiate best practices for designing and implementing solutions around adaptation mechanisms.  ...  management systems. • A taxonomy of adaptation mechanisms that are used to allow autonomous IoT device management. • An overview of different patterns and models that are used to achieve adaptive, autonomous  ... 
doi:10.1109/jiot.2020.3035389 fatcat:d6sxnvnrinhf5efmafs76xiqzm

A Taxonomy and Survey of Intrusion Detection System Design Techniques, Network Threats and Datasets [article]

Hanan Hindy and David Brosset and Ethan Bayne and Amar Seeam and Christos Tachtatzis and Robert Atkinson and Xavier Bellekens
2018 arXiv   pre-print
This manuscript aims to provide researchers with a taxonomy and survey of current dataset composition and current Intrusion Detection Systems (IDS) capabilities and assets.  ...  To this end, this manuscript also provides a taxonomy and survey or network threats and associated tools.  ...  A Taxonomy and Survey of Intrusion Detection System Design Techniques, Network Threats and Datasets :9 A Taxonomy and Survey of Intrusion Detection System Design Techniques, Network Threats  ... 
arXiv:1806.03517v1 fatcat:d6vf2i7gkzbjvm6zb7s6hqcn2e

Using Ontologies in a Cognitive-Grounded System: Automatic Action Recognition in Video-Surveillance

Alessandro Oltramari, Christian Lebiere
2012 Semantic Technologies for Intelligence, Defense, and Security  
For this purpose, we developed a semantic infrastructure on top of a hybrid computational ontology of actions.  ...  This article presents an integrated cognitive system for automatic video surveillance: in particular, we focus on the task of classifying the actions occurring in a scene.  ...  Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein.  ... 
dblp:conf/stids/OltramariL12 fatcat:ynuvip63gna77lxhianzu6sahe
« Previous Showing results 1 — 15 out of 4,311 results