Kontekst w uczeniu się pojęć

• Autorzy: Janina A. Jakubczyc

Warianty tytułu

Context in Concept Learning

• Języki publikacji: PL

Abstrakty

Rosnące woluminy, wzrastająca złożoność, wielość źródeł, a także cele gromadzenia danych różne od realizowanych zadań analizy danych są jedną z przyczyn niepowodzeń algorytmów uczenia się pojęć. Szczególnego znaczenia nabierają upraszczające i nieadekwatne do rzeczywistości założenia. Dotyczą one precyzyjności pojęć, kontekstowej niezależności oraz możliwości reprezentacji pojęcia przez pojedynczy opis symboliczny. Przegląd sposobów uwolnienia tych założeń i poszerzenie opisu pojęć o zależności kontekstowe są przedmiotem artykułu. (abstrakt oryginalny)

EN

Growing volumes and complexity, big number of sources and goals of gathering data that are different than data analysis tasks are the main reason of failure of concept learning algorithms. Simplistic and inadequate to the reality assumptions become significant. They concern accuracy of concepts, contextual independency and possibility to represent concept by a single nominal description. This paper presents an overview of ways to unchain those assumptions and broadening description of concepts by contextual dependency. (original abstract)

Słowa kluczowe

PL

Uczenie się; Proces uczenia się; Automatyczne uczenie się

EN

Studying; Learning process; Automatic learning

• Czasopismo: Prace Naukowe Uniwersytetu Ekonomicznego we Wrocławiu
• Rocznik: 2010
• Numer: nr 133 Pozyskiwanie wiedzy i zarządzanie wiedzą
• Strony: 42--57

Twórcy

autor

Janina A. Jakubczyc

• Uniwersytet Ekonomiczny we Wrocławiu

Bibliografia

• [1] Akman V., Rethinking context as a social construct, "Journal of Pragmatics" 2000, Vol. 32, No. 6, s. 743-759.
• [2] Akman V., Surav M., Steps toward formalizing context, "AI Magazine" 1996, Vol. 17, No. 3, s. 55-72.
• [3] Barve R.D., Long P.M., On the complexity of learning from drifting distributions, "Information and Computation" 1997, Vol. 138, No. 2, s. 101-123.
• [4] Bergadano F., Matwin S., Michalski R. S., Zhang J., Learning two-tiered description of flexible contexts: The POSEIDON system, "Machine Learning" 1992, Vol. 8, No. 1.
• [5] Brézillon P., Some characteristics of context, "Lecture Notes in Computer Science" 2006, Vol. 4031, s. 146-154.
• [6] Brézillon P., Cavalcanti M., Naveiro R., Pomerol J.-Ch., SART: An intelligent assistant for subway control, "Pesquisa Operational, Brazilian Operation Research Society" 2000, Vol. 20, No. 2, s. 247-268.
• [7] Brézillon P., Gonzalez A., Tale of two context-based formalisms for representing human knowledge, "Lecture Notes in Computer Science" 2006, Vol. 4031, s. 137-145.
• [8] Brézillon P., Pomerol J.-Ch., Contextual knowledge sharing and cooperation in intelligent assistant systems, "Le Travail Humain" 1999, Vol. 62, No. 3, s. 223-246.
• [9] Caruana R., Algorithms and Applications for Multi-Task Learning, Proceedings of the 13th International Conference on Machine Learning, Morgan Kaufmann, San Francisco 1996.
• [10] Collins A.M., Quillian M.R., Experiments on semantic memory and language comprehension, [w:] L.W. Gregg (red.), Cognition, Learning and Memory, John Wiley, New York 1972.
• [11] Devaney M., Ram A., Dynamically adjusting concepts to accommodate changing contexts, [w:] Working Notes, ICML-96 Workshop on Learning in Context-Sensitive Domains, Bari, Italy, 1996.
• [12] Domingos P., Context-sensitive feature selection for lazy learners, "Artificial Intelligence Review" 1997, Vol. 11, No. 1-5, s. 227-253.
• [13] Ghidini Ch., Giunchigilia F., Local models semantics, or contextual reasoning = locality+compatibility, "Artificial Intelligence" 2001, Vol. 127, No. 2.
• [14] Harries M.B., Horn K., Learning stable concepts in a changing world, [w:] G. Antoniou, A. Ghose, M. Truczszinski (red.), Lecture Notes on Artificial Intelligence 1359: Learning and Reasoning with Complex Representation, Springer-Verlag, Berlin, New York 1998.
• [15] Harries, M. B., Sammut, C., Horn, K., Extracting hidden context, "Machine Learning" 1998, Vol. 32.
• [16] Helmbold D.P., Long P.M., Tracking drifting concepts by minimizing disagreements, "Machine Learning" 1994, Vol. 1, No. 1 s. 17-45.
• [17] Hirst G., Context as a spurious concept, [w:] Paper Presented at the AAAI-97 Fall Symposium on Context in Knowledge Representation and Natural Language, MIT, Cambridge, Mass., 1997.
• [18] Jakubczyc J., Contextual classifier ensemble for predicting customer churn, [w:] M. Nycz, M. Owoc (red.), Knowledge Acquisition and Management, Research Papers of Wrocław University of Economics No. 25, Publishing House of the Wrocław University of Economics, Wrocław 2008.
• [19] Jakubczyc J., Contextual classifier ensembles, [w:] W. Abramowicz (red.), LNCS 4439 - Business Information Systems, Springer, Berlin, Heidelberg 2007, s. 562-569.
• [20] Jon G.H., Kohavi R., Pfleger K., Irrelevant features and subset selection problem, [w:] W.W. Cohen, H. Hirsh (red.), Machine Learning: Proceedings of the Eleventh International Conference, Morgan Kaufmann Publishers, San Francisco 1994, s. 121-129.
• [21] Katz A.J., Gately M.T., Collins D.R., Robust classifiers without robust features, "Neural Computation" 1990, Vol. 2, s. 471-479.
• [22] Kirizakova I., Kubat M., FAVORIT: Concept formation with ageing of knowledge, "Pattern Recognition Letters" 1992, Vol. 13, nr 1, s. 19-25.
• [23] Klinkenberg R., Learning drifting concepts: Example selection vs. example writhing, "Intelligent Data Analysis" 2004, Special Issue on Incremental Learning Systems Capable of Dealing with Concept Drift, Vol. 8, No. 3, s. 281-300.
• [24] Kubat M., Floating approximation in time-varying knowledge bases, "Pattern Recognition Letters" 1989, Vol. 10, s. 223-227.
• [25] Kubat M., Recycling decision trees in numeric domains, "Informatica" 2000, Vol. 24, No. 3, Slovenia.
• [26] Kubat M., Holte R.C., Matwin S., Machine learning for the detection of oil spills in satellite radar images, "Machine Learning" 1986, Vol. 30, No. 2-3, s. 195-215.
• [27] Kuh A., Petsche T., Rivest R.L., Learning time-varying concepts, [w:] Advances in Neural Information Processing Systems (NIPS), Vol. 3, Morgan Kaufmann, San Francisco, Cal., 1991, s. 183-189.
• [28] Langley P., Gennari J.H., Iba W., Hill-climbing theories of learning, [w:] Proceedings of the Fourth International Workshop on Machine Learning, Morgan Kaufman, Los Altos, Cal., 1987, s. 312-323.
• [29] Lenat D.B., Guha R.V., Ideas for Applying CYC, Cycorp, Inc., http://www.cyc.com/techreports/ act- cyc-407-91/act-cyc-407-91.html, 1991 (dostępny 22.12. 2008).
• [30] Letourneau S., Famili A.F., Matwin S., A normalization method for contextual data: Experience from a large-scale application, Machine Learning: EMCL-98, "Lecture Notes in Computer Science" 1998, Vol. 1398, s. 49-54.
• [31] Littlestone N., Learning quickly when relevant attributes abound: New linear-threshold algorithm, "Machine Learning" 1988, Vol. 2, No. 4, s. 285-318.
• [32] Matwin S., Kubat M., The role of context in concept learning, [w:] Proceedings of the ICML-96 Workshop on Learning in Context-Sensitive Domains, Bari 1996, s. 1-5.
• [33] Michalski R.S., Concepts as Flexible and Context-dependent Sets: The Two-tiered View, Technical Report, Mason Archival Repository Service, 1991, http://hdl.handle.net/1920/1688 (dostępny 23.03.2009).
• [34] Michalski R.S., Learning flexible concepts: Fundamental ideas and methods based on twotiered representation, [w:] Machine Learning: An Artificial Intelligence Approach, Vol. 3, Morgan Kaufmann Publishers, San Mateo, Cal., 1990.
• [35] Minsky M., A framework for representing knowledge, [w:] P. Winston (red.), The Psychology of Computer Vision, McGraw-Hill, New York 1975.
• [36] Mittchell T., Caruana R., Freitag D., McDermott J., Zabowski D., Experience with a learning personal assistant, "Communications of the ACM" 1994, Vol. 37, No. 7. s. 80-91.
• [37] Motschnig-Pitrik R., An integrated view on the viewing abstraction: Contexts and perspectives in software development, AI, and Databases, "Journal of Systems Integration" 1995, Vol. 5, No. 1, s. 23-60.
• [38] Palmquist M., The Role of Context in Shaping Purpose and Constructing Meaning, http://writing.colostate.edu/guides/processes/writingsituations/conclusion.cfm (dostępny 23.03.2009).
• [39] Powell G., Matheus C., Kokar M., Lorenz D., Understanding the role of context in the interpretation of complex battlespace intelligence, [w:] Proceedings of the Ninth International Conference on Information Fusion, 2006, http://handle.dtic.mil/100.2/ADA457435.
• [40] Ramsey C.L., Grefenstette J.J., Case-based initialization of genetic algorithms, [w:] Proceedings of the 5th International Conference on Genetic Algorithms, Morgan Kaufman, San Mateo, Cal., 1993.
• [41] Salganicoff M., Destiny-adaptive learning and forgetting, [w:] Proceedings of the Tenth International Conference on Machine Learning, Morgan Kaufmann, San Mateo, Cal., 1993, s. 276-283.
• [42] Salganicoff M., Tolerating concept and sampling shift in lazy learning using prediction error context switching, "Artificial Intelligence Review" 1997, Vol. 11, s. 133-155.
• [43] Schlimmer J.C., Granger R.H., Incremental learning from noisy data, "Machine Learning" 1986, Vol. 1, s. 317-354.
• [44] Smith E.E., Medin D.L., Categories and Concepts, Harvard University Press, Cambridge, Mass., 1981.
• [45] Sowa J., Peircean foundations for a theory of context, "Lecture Notes in Computer Science", Proceedings of the International Conference on Conceptual Structures: Fulfilling Peirce's Dream, Springer-Verlag, London 1997, s. 41-54.
• [46] Terziyan V.Y., Puuronen S., Multilevel context representation using semantic meta network, "International Journal of Medical Informatics" 1998, Elsevier.
• [47] Theodorakis M., Analyti A., Constantopoulos P., Spyratos N., A theory of contexts, [w:] Information Bases. Technical Report 216, Institute of Computer Science Foundation for Research and Technology - Hellas, March 1998.
• [48] Tomaszewski T. (red.), Pamięć. Uczenie się. Język, Wydawnictwo Naukowe PWN, Warszawa 1995.
• [49] Tomaszewski T., Grabowska A., Budohoska W., Kozielecki J., Percepcja. Myślenie decyzyjne, Wydawnictwo Naukowe PWN, Warszawa 1995.
• [50] Tsymbal A., Pechenizkiy M., Cunnigham P., Puuronen S., Dynamic integration of classifiers for tracking concept drift in antibiotic resistance data, Computer Science Technical Report TCD-CS-2005-26, Trinity College Dublin, Department of Computer Science, https://www.cs.tcd.ie/publications/tech-reports/reports.05/TCD-CS-2005-26.pdf (dostępny 23.03.2009).
• [51] Turney P.D., Exploiting context when learning to classify, [w:] Proceedings of the Sixth European Conference on Machine Learning, Springer-Verlag, Berlin 1993.
• [52] Turney, P.D., The identification of context-sensitive features: A formal definition of context for concept learning, [w:] 13th International Conference on Machine Learning (ICML96), Workshop on Learning in Context-Sensitive Domains, Bari, Italy, July 1996, s. 53-59.
• [53] Turney, P.D., The management of context-sensitive features: A review of strategies, [w:] 13th International Conference on Machine Learning (ICML96), Workshop on Learning in Context-Sensitive Domains, Bari, Italy, July 1996, s. 60-66.
• [54] Turney P.D., Halasz M., Contextual normalization applied to aircraft gas turbine engine diagnosis, "Journal of Applied Intelligence" 1993, Vol. 3, No. 2, s. 109-129.
• [55] Wang Y., Joshi M., Rose C., Fisher F., Weinberger A., Stegmann K., Context based classification for automatic collaborative learning process analysis, [w:] Frontiers in Artificial Intelligence and Applications. Proceeding of the Conference on Artificial Intelligence in Education: Building Technology Rich Learning Contexts That Work, 2007, Vol. 158, s. 662-664.
• [56] Watrous R.L., Speaker normalization and adaptation using second-order connectionist networks, "IEEE Transaction on Neural Networks" 1993, Vol. 4, No. 1, s. 21-30.
• [57] Watrous R.L, Towell G., A patient-adaptive neural network ECG patient monitoring algorithm, Computers in Cardiology, Siemens Corp. Res. Inc., Princeton, NJ, 1995. s. 229-232.
• [58] Widmer G., Combining robustness and flexibility in learning drifting concepts, [w:] Proceedings of the Eleventh European Conference on Artificial Intelligence, Wiley, Chichester 1994.
• [59] Widmer G., Recognition and exploitation of contextual clues via incremental meta-learning, [w:] Proceedings of the 13th International Conference on Machine Learning, Morgan Kaufmann, San Francisco, Cal., 1996.
• [60] Widmer G., Tracking context changes through meta-learning, "Machine Learning Journal" 1997, Vol. 27, No. 3, s. 2755-2790.
• [61] Widmer G., Kubat M., Effective learning in dynamic environments by explicit context tracking, [w:] Proceedings of the Sixth European Conference on Machine Learning, Springer-Verlag, Berlin 1993.
• [62] Widmer G., Kubat M., Learning flexible concepts from streams of examples: FLORA2, [w:] Proceedings of the 10th European Conference on Artificial Intelligence, Wiley, Chichester, UK, 1992.
• [63] Widmer G., Kubat M., Learning in the presence of concept drift and hidden contexts, "Machine Learning" 1986, Vol. 23, No. 1, s. 69-101.