Solving problems of contextual nature by neural nets

• Autorzy: Ciskowski P.
• Języki publikacji: EN

Abstrakty

EN

The paper addresses the problem of using contextual information by neural nets solving problems of contextual nature. Various approaches towards contextual machine learning from literature art analyzed. The model of context-dependent neuron is presented as well as the theoretical backgrounds for using context-dependent weights. Examples of dis-criminating boundaries produced by traditional and context-dependent nets art compared. The advantages of context-dependent nets in solving contextual classification tasks art shown.

Słowa kluczowe

EN

neutral nets; solving contextual problems; context-dependent nets

• Wydawca: Wydawnictwo Politechniki Częstochowskiej
• Czasopismo: Informatyka Teoretyczna i Stosowana
• Rocznik: 2003
• Tom: R. 3, nr 4
• Strony: 19--37
• Opis fizyczny: Bibliogr. 30 poz., 10 rys.

Twórcy

autor

Ciskowski P.

• Instytut Cybernetyki Technicznej, Politechnika Wrocławska Wybrzeże Wyspiańskiego 27, 50-370 Wrocław

Bibliografia

• [1] Bekey G.A., Yeung D.T., Using a context-sensitive learning for robot arm control, Proceedings of IEEE International Conference on Robotics and Automation, Scottsdale, Arizona, May 14-19 1989, 1441-1447.
• [2] Bekey G.A., Yeung D.T., On Reducing Learning Time in Context-Dependent Mappings, IEEE Transactions on Neural Networks 1993, 4, 1, January.
• [3] Bishop C.M., Neural Networks for Pattern Recognition, Clarendon Press, Oxford 1996.
• [4] Bishop C.M., Jordan M.I., Neural Networks, CRC Handbook of Computer Science, CRC Press, Boca Raton 1996.
• [5] Ciskowski P., Learning of context-dependent neural nets, PhD thesis, Wroclaw University of Technology, Wroclaw 2002.
• [6] Harries M.B., Batch Learning in Domains with Hidden Changes in Context, PhD thesis, University of NSW, 1999.
• [7] Harries M.B., Sammut C., Horn K., Extracting Hidden Context, Machine Learning, 32, 101-126.
• [8] Harries M.B., Horn K., Sammut C., Learning in Time Ordered Domains with Hidden Changes in Context.
• [9] Harries M.B., Horn K., Learning stable concepts in domains with hidden changes in context. Learning in context-sensitive domains (Workshop Notes), 13th International Conference on Machine Learning, Bari, Italy 1996.
• [10] Hecht-Nielsen R., Neurocomputing, Addison Wesley, Amsterdam 1991.
• [11] Kolmogorov A.N., On the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition, DokI. Akad. Nauk ZSRR 1957, 114, 953-956.
• [12] Kubat M., Second tier for decision trees, Proceedings of the 13th Internal Conference, MachineLearning: California, Morgan Kaufman 1996,293-301.
• [13] Kubat M., Pfurtscheller G., Flotzinger D., AI-Based Approach to Automatic Sleep Classification,Biological Cybernetics 1994, 79, 443-448.
• [14] Lawrence S., Burns L., Back A., Tsoi A.C., Giles C.L., Neural Network Classification and Prior Class Probabilities, Tricks of the Trae, Lecture Notes in Computer Science State-of-the-art,Springer- Verlag, Surveys 1998, 299-314.
• [15] Matwin S., Kubat M., The Role of Context in Concept Learning, Learning in context-sensitivedomains (Workshop Notes), 13th International Conference on Machine Learning, Bari, Italy1996.
• [16] Osowski S., Neural nets, AIgorithmic approach (in Polish), WNT, Warszawa 1996.
• [17] Pratt L.Y., Discriminability-Based Transfer between Neural Networks, Advances in Neural Information Processing Systems 5, Kaufman, San Mateo, California 1993, 204-211.
• [18] Pratt L.Y., Transfer between Neural Networks to Speed up Learning, Journal of Artificial Intelligence Research.
• [19] Pratt L.Y., Mostow J., Kamm C.A.,Direct Transfer of Learned Information among Neural Networks,Proceedings ofthe 9th National Conference on Artificial Intelligence AAAI-91, Anheim,California 1999, 584-590.
• [20] Rafajłowicz E., Context-dependent neural nets - problem statement and examples, Proceedings of the Third Conference Neural Networks and their Applications, Zakopane, Poland, May 1999.
• [21] Rafajłowicz E., Learning of context-dependent neural nets, Proceedings of the Third ConferenceNeural Networks and their Applications, Zakopane, Poland, May 1999.
• [22] Tibshirani R., Hinton G., Coaching variables for regression and classification, Statistics andComputing 1998, 8, 25-33.
• [23] Turney P., The Identification of Context-Sensitive Features: A FormaI Definition of Context forConcept Learning, Proceedings of 13th International Conference on Machine Learning ICML96,Workshop on Learning in Context-Sensitive Domains, Bari, Italy 1996.
• [24] Turney P., The Management of Context-Sensitive Features: A Review of Strategies, Proceedingsof 13th International Conference on Machine Learning ICML96, Workshop on Learning inContext-Sensitive Domains, Bari, Italy 1996.
• [25] Watrous R., Towell G., A Patient-Adaptive Neural Network ECG Patient Monitoring Algorithm,Computers in Cardiology, Vienna, Austria, September 10-13, 1995.
• [26] Watrous R.L., Context-modulated vowel discrimination using connectionist networks, Computer Speech and Language 1991, 5, 341-362.
• [27] Watrous R.L., Speaker normalization and adaptation using second-order connectionist networks,IEEE Transactions on Neural Networks 1993,4(1), 21-30, January.
• [28] Watrous R.L., Speech Recognition using Connectionist Networks, PhD thesis, University of Pennsylvania, 1988.
• [29] Widmer G., Tracking Context Changes through Meta-Learning, Machine Learning 1997, 27, 259-286.
• [30] Widmer G., Kubat M., Learning in the presence of concept drift and hidden contexts, Machine Learning 1996, 23, 69-101.