Learning from examples, agent teams and the concept of reflection

International Journal of Pattern Recognition and Artificial Intelligence

Volumn 10, Issue 3, 1996, Pages 251-272

  Beyer, Uwe ^a,b   Śmieja, Frank J ^a,c,d  

^a FRAUNHOFER INSTITUTE FOR APPLIED INFORMATION TECHNOLOGY FIT   (Germany)

^b UNIVERSITY OF BONN   (Germany)

^c UNIVERSITY OF OXFORD   (United Kingdom)

^d UNIVERSITY OF EDINBURGH   (United Kingdom)

Author keywords

Agent accuracy; Approximation rate; Confidence; Reflection; Team

Indexed keywords

AGENTS; REFLECTION;

ACCURACY; APPROXIMATION; CONFIDENCE; EXEMPLE BASED LEARNING; MODELING;

LEARNING ALGORITHMS;

EID: 0030356761     PISSN: 02180014     EISSN: None     Source Type: Journal    
DOI: 10.1142/S0218001496000190     Document Type: Article

References (34)

1. E. Baum and D. Haussler, "What size net gives valid generalization?" Neural Computation 1 (1989) 151.
2. U. Beyer and F, J. Smieja, "Quantitative aspects of data-driven information processing", Technical Report 732, GMD - German National Research Center for Information Technology, Sankt Augustin, Germany, Mar. 1993.
3. A. Blumer, A. Ehrenfeucht, D. Haussler and M. Warmuth. "Learnability and the Vapnik-Chervonenkis dimension", J. ACM 36, 4 (1989) 929.
4. Belur V. Dasarathy, Nearest Neighbor (NN) Norms: NN Pattern Classification Techniques, IEEE Computer Society Press, Los Alamos, 1986.
5. A. P. Dempster, "Upper and lower probabilities induced by a multivalued mapping". Annals of Mathematical Statistics 38 (1967) 325-339.
6. B. Efron, "Bootstrap methods: Another look at the jackknife", The Annals of Statistics 7, 1 (1979) 1-26.
7. J. Franke and E. Mandler, "A comparison of two approaches for combining the votes of cooperating classifiers", in Proc. 11th IAPR, Den Haag, Netherlands, 1992, pp. 611-614.
8. S. Geman, E. Bienenstock, and R. Doursat, "Neural networks and the bias/variance dilemma", Neural Computation 4 (1992) 1-58.
9. J. B. Hampshire and B. A. Pearlmutter, "Equivalence proofs for multi-layer perceptron classifiers and the Bayesian discriminant function", in Proc 1990 Connectionist Models Summer School, eds. Touretzky, Elman, Sejnowski and Hinton, San Mateo, CA, 1990.
10. S. Hubrig-Schaumburg, "Handwritten character recognition using a reflective modular neural network system", Diploma thesis, GMD, November 1992, unpublished.
11. R. A. Jacobs and M. I. Jordan, "Adaptive mixtures of local experts", Neural Com putation 3, 1 (1991).
12. V. Jagannathan, R. Dodhiawala, and L. Baum, eds., Blackboard Architectures and Applications, Academic Press, Inc, 1989.
13. K. Joe, Y. Mori, and S. Miyake, "Construction of a large-scale neural network: Simulation of handwritten Japanese character recognition on NCUBE",Concurrency, Practice and Experience 2, 2 (1990) 79-107.
14. A. Linden and F. Weber, "Implementing inner drive by competence reflection", in Proc. 2nd Int. Conf. on Simulation of Adaptive Behavior, Hawaii, 1992.
15. E. Mandler and J. Schürmann, "Combining the classification results of independent classifiers based on the Dempster-Schafer theory of evidence", in Pattern Recognition and Artificial Intelligence, eds. E. S. Gelsema and L. N. Kanal, Eisevier Science Publishers B. V. North-Holland, Amsterdam, 1988, pp. 381-394.
16. H. Mühlenbein and D. Schlierkamp-Voosen, "Predictive models for the breeder genetic algorithm: Continuous parameter optimization". Evolutionary Computation, 1 (1993).
17. National Institute of Standards and Technology, OCR-system conference, Technical Report NISTIR 4912, NIST, Gaithersburg MD, Aug. 1992.
18. Stephen Omohundro, "Geometric learning algorithms", Technical Report TR-89-041, Berkeley, 1989.
19. N. Otsu, "Nonlinear discriminant analysis as a natural extension of the linear case", Behaviormetrika 2 (1975) 24-59.
20. T. L. D. Regulinski, "On reliability of expert systems", IEEE Trans. Reliability, 40, 4 (1991) 401.
21. D. L. Reilly, C. Scofield, C. Elbaum and L. N. Cooper, "Learning system architectures composed of multiple learning modules", in IEEE First Int. Conf. on Neural Networks, 1987, pp. 495-503.
22. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning internal representations by error propagation", Nature 323, 533 (1986).
23. P. Smets, E. Mamdani, D. Dubois and H. Prade, eds., Non-standard Logics for Automated Reasoning, Academic Press, 1988, pp. 253-286.
24. F. J. Śmieja, "Multiple network systems (MINOS) modules: Task division and module discrimination", in Proc. 8th AISB Conf. on Artificial Intelligence, Leeds, Apr. 1991; Also available as GMD Technical Report 638.
25. F. J. Śmieja, "Neural network constructive algorithms: Trading generalization for learning efficiency?" Circuits, Systems and Signal Processing, 12, 2 (1993) 331-374.
26. F. J. Smieja, The Pandemonium system of reflective agents, IEEE Transactions on Neural Networks 7, 1 (1996), (in press).
27. F. J. Smieja, "Rejection of incorrect answers from a neural net classifier", in New Trends in Neural Computation (Proc. IWANN 93), eds. J. Mira, J. Cabestany and A. Prieto, Lecture Notes in Computer Science 686, Springer-Verlag, 1993.
28. F. J. Smieja and U. Beyer, "JANUS: A robot manipulator system based on a black-board architecture", Technical Report 839, GMD - German National Research Center for Information Technology, Sankt Augustin, Germany, April 1994; Poster presentation in AICS '94.
29. F. J. Smieja and H. Mühlenbein, "Reflective modular neural network systems", Technical Report 633, GMD - German National Research Center for Information Technology, Sankt Augustin, Germany, Feb. 1992.
30. L. G. Valiant, "A theory of the learnable", Commun. ACM 27, 11 (1984) 1134-1142.
31. G. Wahba, C. Gu, Y. Wang and R. Chappell, "Soft classification, a.k.a. risk estimation, via penalized log likelihood and smoothing spline analysis of variance", Technical Report 899, University of Wisconsin, Jan. 1993.
32. A. Waibel, "Modular construction of time-delay neural networks for speech recognition", Neural Computation, 1 (1989).
33. D. H. Wolpert, " Stacked generalization", Technical Report LA-UR-90-3460, LANL, Los Alamos, NM, 1990.
34. B.-T. Zhang and G. Veenker, "Neural networks that teach themselves through genetic discovery of novel examples", Int. Joint Conf. on Neural Networks (IJCNN-91), Vol. 1, pp 690-695; IEEE and INNS, 1991.