A Bound on Modeling Error in Observable Operator Models and an Associated Learning Algorithm

Neural Computation

Volumn 21, Issue 9, 2009, Pages 2687-2712

  Zhao, Ming Jie ^a   Jaeger, Herbert ^a   Thon, Michael ^a  

^a JACOBS UNIVERSITY BREMEN   (Germany)

Author keywords

[No Author keywords available]

Indexed keywords

EFFICIENCY; ERRORS; HIDDEN MARKOV MODELS; IMAGE SEGMENTATION; LINEAR TRANSFORMATIONS; MAXIMUM PRINCIPLE; TRELLIS CODES;

HIDDEN-MARKOV MODELS; MATHEMATICAL THEORY; MATRIX FORMALISM; MODEL ERRORS; OBSERVABLE OPERATOR MODELS; OPTIMALITY CRITERIA; OPTIMISATIONS; OPTIMIZATION TASK; STATISTICAL EFFICIENCY; TRANSFORMATION MATRIX;

LEARNING ALGORITHMS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; HUMAN; LEARNING; PHYSIOLOGY; PROBABILITY; STATISTICAL MODEL;

ALGORITHMS; ASSOCIATION LEARNING; HUMANS; MARKOV CHAINS; MODELS, STATISTICAL; NEURAL NETWORKS (COMPUTER);

EID: 70349239285     PISSN: 08997667     EISSN: 1530888X     Source Type: Journal    
DOI: 10.1162/neco.2009.01-08-687     Document Type: Article

References (29)

1. Bengio, Y. (1999). Markovian models for sequential data. Neural Computing Surveys, 2, 129–162.
2. Bourlard, H., & Bengio, S. (2002). Hidden Markov models and other finite state automata for sequence processing. In M. A. Arbin (Ed.), The handbook of brain theory and neural networks (2nd ed.). Cambridge, MA: MIT Press.
3. Bowling, M., McCracken, P., James, M., Neufeld, J., & Wilkinson, D. (2006). Learning predictive state representations using non-blind policies. In Proceedings of the 23rd International Conference on Machine Learning (ICML) (pp. 129–136). New York: ACM.
4. Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood from incomplete data via the EM-algorithm. Journal of the Royal Statistical Society, 39(1), 1–38.
5. Durbin, R., Eddy, S., Krogh, A., & Mitchinson, G. (2000). Biological sequence analysis: Probabilistic models of proteins and nucleic acids. Cambridge: Cambridge University Press.
6. Faigle, U., & Schönhuth, A. (2006). Quantum predictor models. Electronic Notes in Discrete Mathematics, 25, 149–155.
7. Faigle, U., & Schönhuth, A. (2007). Asymptotic mean stationarity of sources with finite evolution dimension. IEEE Transactions on Information Theory, 53, 2342– 2348.
8. Gusfield, D. (1997). Algorithms on strings, trees, and sequences: Computer science and computational biology. Cambridge: Cambridge University Press.
9. Jaeger, H. (1998). Discrete-time, discrete-valued observable operator models: A tutorial (GMD Rep. 42). Sankt Augustin, Germany: German National Research Center for Information Technology.
10. Jaeger, H. (1999). Characterizing distributions of stochastic processes by linear operators (GMD Rep. 62). Sankt Augustin, Germany: German National Research Center for Information Technology.
11. Jaeger, H. (2000a). Modeling and learning continuous-valued stochastic processes with OOMs (GMD Rep. 102). Sankt Augustin, Germany: German National Research Center for Information Technology.
12. Jaeger, H. (2000b). Observable operator models for discrete stochastic time series. Neural Computation, 12(6), 1371–1398.
13. Jaeger, H., Zhao, M., Kretzschmar, K., Oberstein, T. G., Popovici, D., & Kolling, A. (2005). Learning observable operator models via the ES algorithm. In S. Haykin, J. Principe, T. Sejnowski, & J. McWhirter (Eds.), New directions in statistical signal processing: From systems to brains. Cambridge, MA: MIT Press.
14. James, M. R., & Singh, S. (2004). Learning and discovery of predictive state representations in dynamical systems with reset. In Proceedings of the 21st International Conference on Machine Learning (ICML: pp. 53–60). New York: ACM.
15. Jelinek, F. (1998). Statistical methods for speech recognition. Cambridge, MA: MIT Press.
16. Kretzschmar, K. (2003). Learning symbol sequences with observable operator models. (GMD Rep. 161). Sankt Augustin, Germany: Fraunhofer Institute AIS.
17. Kuhn, H. W., & Tucker, A. W. (1951). Nonlinear programming. In Proceedings of 2nd Berkeley Symposium (pp. 481–492). Berkeley: University of California Press.
18. Littman, M. L., & Sutton, R. S. (2001). Predictive representation of state. In T. G. Dietterich, S. Becker, & Z. Ghahramani (Eds.), Advances in neural information processing systems, 14 (pp. 1555–1561). Cambridge, MA: MIT Press.
19. McCracken, P., & Bowling, M. (2005). Online discovery and learning of predictive state representations. In Y. Weiss, B. Schölkopf, & J. Platt (Eds.), Advances in neural information processing systems, 18 (pp. 875–882). Cambridge, MA: MIT Press.
20. Pesin, Y. B. (1977). Characteristic Lyapunov exponents and smooth ergodic theory. Russ. Math. Surveys, 32(4), 55–114.
21. Rabiner, L. R. (1989). A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 77(2), 257–286.
22. Rudary, M., & Singh, S. (2006). Predictive linear-gaussian models of controlled stochastic dynamical systems. In Proceedings of the 23rd International Conference on Machine Learning (ICML, pp. 777–784). New York: ACM.
23. Schönhuth, A. (2006). Diskretwertige stochastische Vektorräume. Unpublished doctoral dissertation, University Köln.
24. Singh, S., Littman, M. L., Jong, N. K., Pardoe, D., & Stone, P. (2003). Learning predictive state representations. In Proceedings of the 20th International Conference on Machine Learning (ICML, pp. 712–719). New York: ACM.
25. Ukkonen, E. (1995). On-line construction of suffix trees. Algorithmica, 14(3), 249– 260.
26. Wingate, D., & Singh, S. (2007). On discovery and learning of models with predictive state representations of state for agents with continuous actions and observations. In Procedings of the 6th International Conference on Autonomous Agents and Multiagent Systems (AAMAS). New York: ACM.
27. Wolfe, B. (2006). Predictive state representations with options. In Proceedings of the 23rd International Conference on Machine Learning (ICML, pp. 1025–1032). New York: ACM.
28. Wolfe, B., James, M. R., & Singh, S. P. (2005). Learning predictive state representations in dynamical systems without reset. In Proceedings of the 22nd International Conference on Machine Learning (ICML, pp. 985–992). New York: ACM.
29. Zhao, M.-J., & Jaeger, H. (2007). Norm observable operator models (Tech. Rep. 8). Bremen: Jacobs University.