Filters








6,301 Hits in 7.2 sec

Combining Data-driven Supervision with Human-in-the-loop Feedback for Entity Resolution [article]

Wenpeng Yin, Shelby Heinecke, Jia Li, Nitish Shirish Keskar, Michael Jones, Shouzhong Shi, Stanislav Georgiev, Kurt Milich, Joseph Esposito, Caiming Xiong
2021 arXiv   pre-print
In this case study, we discuss our human-in-the-loop enabled, data-centric solution to closing the training-production performance divergence.  ...  Tasked with building an entity resolution system - a model that identifies and consolidates data points that represent the same person - our first model exhibited a clear training-production performance  ...  Discussion In this case study, we shared our human-in-the-loop-enabled, data-centric approach for building a production quality entity resolution model.  ... 
arXiv:2111.10497v1 fatcat:m7wkmilsivfmre5d2tf6bttt3q

NOUS: Construction and Querying of Dynamic Knowledge Graphs

Sutanay Choudhury, Khushbu Agarwal, Sumit Purohit, Baichuan Zhang, Meg Pirrung, Will Smith, Mathew Thomas
2017 2017 IEEE 33rd International Conference on Data Engineering (ICDE)  
The uniqueness of our system lies A) in its combination of curated KGs along with knowledge extracted from unstructured text, B) support for advanced trending and explanatory questions on a dynamic KG,  ...  and C) the ability to answer queries where the answer is embedded across multiple data sources.  ...  We would also like to thank the OpenKE team at Laboratory for Analytic Sciences for their continuous support and feedback.  ... 
doi:10.1109/icde.2017.228 dblp:conf/icde/ChoudhuryAPZPST17 fatcat:g7kzogldv5ahdig7i7u5epmgda

NOUS: Construction and Querying of Dynamic Knowledge Graphs [article]

Sutanay Choudhury and Khushbu Agarwal and Sumit Purohit and Baichuan Zhang and Meg Pirrung and Will Smith and Mathew Thomas
2016 arXiv   pre-print
The uniqueness of our system lies A) in its combination of curated KGs along with knowledge extracted from unstructured text, B) support for advanced trending and explanatory questions on a dynamic KG,  ...  and C) the ability to answer queries where the answer is embedded across multiple data sources.  ...  We would also like to thank the OpenKE team at Laboratory for Analytic Sciences for their continuous support and feedback.  ... 
arXiv:1606.02314v1 fatcat:vgm6fiorafbpfp56uafxyyj2fe

Extreme Extraction: Only One Hour per Relation [article]

Raphael Hoffmann, Luke Zettlemoyer, Daniel S. Weld
2015 arXiv   pre-print
Supervised learning requires copious human annotation, while unsupervised and weakly supervised approaches do not deliver competitive accuracy.  ...  We present a novel system, InstaRead, that streamlines authoring with an ensemble of methods: 1) encoding extraction rules in an expressive and compositional representation, 2) guiding the user to promising  ...  INSTAREAD is designed to address the inefficiencies identified in Section 2 with the combination of an expressive rule language, data-driven guidance to new rules, and instant rule execution.  ... 
arXiv:1506.06418v1 fatcat:b7h3yngagzfadhs5nqqaiult7q

The human is the loop: new directions for visual analytics

Alex Endert, M. Shahriar Hossain, Naren Ramakrishnan, Chris North, Patrick Fiaux, Christopher Andrews
2014 Journal of Intelligent Information Systems  
We argue for a shift from a 'human in the loop' philosophy for visual analytics to a 'human is the loop' viewpoint, where the focus is on recognizing analysts' work processes, and seamlessly fitting analytics  ...  We survey a range of projects that provide visual analytic support contextually in the sensemaking loop, and outline a research agenda along with future challenges. A. Endert Pacific  ...  Acknowledgements This work is supported in part by the Institute for Critical Technology and Applied Science, Virginia Tech, and the US National Science Foundation through grant CCF-0937133.  ... 
doi:10.1007/s10844-014-0304-9 fatcat:mnq2g4zq6ve77cmuyq42mgb7zm

From 'Understanding the Brain by Creating the Brain' towards manipulative neuroscience

M. Kawato
2008 Philosophical Transactions of the Royal Society of London. Biological Sciences  
I argue that the major reason for this difference is that essential information can be experimentally manipulated in molecular and cellular neuroscience while it cannot be manipulated at the system level  ...  Here, we aim to understand the brain to the extent that we can make humanoid robots solve tasks typically solved by the human brain by essentially the same principles.  ...  for crossing the MAP kinase-positive feedback loop threshold and inducing LTD.  ... 
doi:10.1098/rstb.2008.2272 pmid:18375374 pmcid:PMC2610191 fatcat:ci6zc3nq7fdobhxw5win7d5ed4

Intent-driven Closed Loops for Autonomous Networks

Pedro Henrique Gomes, Magnus Buhrgard, János Harmatos, Swarup Kumar Mohalik, Dinand Roeland, Jörg Niemöller
2021 Journal of ICT Standardization  
loop in the hierarchy needs to account for.  ...  The new capabilities introduced in this paper can be considered as an extension of the ZSM framework to be used in scenarios where multiple intent-driven closed loops exist.  ...  The primary data and control flow of the CL model shown in Figure 2 starts with the collection stage, which is responsible for collecting and preprocessing data coming from the managed entity.  ... 
doi:10.13052/jicts2245-800x.929 fatcat:a4dz24nwpfdt3lycp25cz7many

Methods of AI for Multimodal Sensing and Action for Complex Situations

Erik Blasch, Robert Cruise, Alexander Aved, Uttam Majumder, Todd Rovito
2019 The AI Magazine  
Decisions-to-data combines AI computational capabilities with human reasoning to manage data collections, perform data fusion, and assess complex situations (that is, context reasoning).  ...  in collect), (4) software computing (data in transit), and (5) human–machine AI (data in use).  ...  We then discusses the dynamic data-driven applications systems (DDDAS) paradigm for using models (data in transit). The Human-Machine AI section discusses humanmachine teaming (data in use).  ... 
doi:10.1609/aimag.v40i4.4813 fatcat:mfjsclsdsjek7blltazmtwftd4

Improving Publication Pipeline with Automated Biological Entity Detection and Validation Service

Weijia Xu, Amit Gupta, Pankaj Jaiswal, Crispin Taylor, Patti Lockhart, Jennifer Regala
2019 Data and Information Management  
The updates can then be used to improve the entity detection in subsequent processed articles in the future. We describe our framework and deployment in details.  ...  These extracted entities are then stored in a database and made accessible through an interactive web application for curation and evaluation by authors.  ...  The application integrates multiple NLP methods for entity recognition and enables human curation to close the feedback loop.  ... 
doi:10.2478/dim-2019-0003 fatcat:w4swautdkbefti3gfy4scsle5u

Intelligent manufacturing systems

David A. Tansik, Ann Majchrzak
1990 Journal of Technology Transfer  
The Intelligent Systems Architecture for Manufacturing (ISAM) addresses the application of intelligent systems to the manufacturing enterprise at three degrees of abstraction: 1) a conceptual framework  ...  for developing metrics, standards, and performance measures, 2) a reference model architecture for conceptual design of intelligent systems, and 3) a set of engineering guidelines for the implementation  ...  Thus, reactive feedback loops are simultaneously closed at all levels of resolution in space and time.  ... 
doi:10.1007/bf02371524 fatcat:eskdsgwwrrhsfibsow3rnziqvi

Intelligent Manufacturing Systems

Andrew Kusiak, David Dornfeld
1991 Journal of Engineering for Industry  
The Intelligent Systems Architecture for Manufacturing (ISAM) addresses the application of intelligent systems to the manufacturing enterprise at three degrees of abstraction: 1) a conceptual framework  ...  for developing metrics, standards, and performance measures, 2) a reference model architecture for conceptual design of intelligent systems, and 3) a set of engineering guidelines for the implementation  ...  Thus, reactive feedback loops are simultaneously closed at all levels of resolution in space and time.  ... 
doi:10.1115/1.2899693 fatcat:klnrqr6hajedner6abtxpd7kwu

Self-adaptive systems: A survey of current approaches, research challenges and applications

Frank D. Macías-Escrivá, Rodolfo Haber, Raul del Toro, Vicente Hernandez
2013 Expert systems with applications  
These natural self-adaptive systems have attracted the attention of software designers, because of the ease with which they can change their own behavior in response to changes in their environment (Nakagawa  ...  Finally, the main bottlenecks for the effective application of self-adaptive technology, as well as a set of key research issues on this topic, are precisely identified, in order to overcome current constraints  ...  We are also grateful to Antony Price for his assistance with the editing of this paper.  ... 
doi:10.1016/j.eswa.2013.07.033 fatcat:2gz76hptsfcd7cd2ztd3htaew4

An Outlook on the Interplay of Machine Learning and Reconfigurable Intelligent Surfaces: An Overview of Opportunities and Limitations [article]

Lina Mohjazi, Ahmed Zoha, Lina Bariah, Sami Muhaidat, Paschalis C. Sofotasios, Muhammad Ali Imran, Octavia A. Dobre
2021 arXiv   pre-print
A review of the state-of-the-art research on the integration of ML with RISs is presented, highlighting their potentials as well as challenges.  ...  Finally, the paper concludes by offering a look ahead towards unexplored possibilities of ML mechanisms in the context of RISs.  ...  In RL, a feedback loop exists between the environment and the algorithm, allowing it to adaptively converge to an ideal behavior leveraging the feedback received from the environment.  ... 
arXiv:2004.00365v2 fatcat:li5tb3ylrjcujkjdbu2wdy5ggu

Alexa Prize — State of the Art in Conversational AI

Chandra Khatri, Anu Venkatesh, Behnam Hedayatnia, Raefer Gabriel, Ashwin Ram, Rohit Prasad
2018 The AI Magazine  
that can converse coherently and engagingly with humans on popular topics for 20 minutes.  ...  To build their socialbots, the students combined state-of-the-art techniques with their own novel strategies in the areas of Natural Language Understanding and Conversational AI.  ...  Acknowledgments We would like to thank all the university students and their advisors (Alexa Prize Teams 2017) who participated in the competition.  ... 
doi:10.1609/aimag.v39i3.2810 fatcat:kuprycf7gbdvjiuf33b5ylmfli

Multidisciplinary and Historical Perspectives for Developing Intelligent and Resource-Efficient Systems

Aarne Mammela, Jukka Riekki, Adrian Kotelba, Antti Anttonen
2018 IEEE Access  
The general, long-standing problem to be tackled is multiobjective optimization with autonomous and distributed decision-making in an uncertain, dynamic, and nonlinear environment where the objectives  ...  Optimization, decision-making, open-and closed-loop control, hierarchy, and degree of centralization turn out to be recurring themes in these disciplines, which have converged to similar solutions that  ...  In many cases, the optimum cannot be found with a feedback loop only, but it is found in two phases called acquisition and tracking [208] , [294] where open and closed-loop control are combined.  ... 
doi:10.1109/access.2018.2816605 fatcat:uquofyjyazgu3hzsxjugpso76a
« Previous Showing results 1 — 15 out of 6,301 results