Abstract
In this chapter, we consider the issue of Hidden Markov Model (HMM) training. First, HMMs are introduced and then we focus on the particular HMM training problem. We emphasize the difficulty of this problem and present various criteria that can be considered.Many different adaptations of metaheuristics have been used but, until now, few extensive comparisons have been performed for this problem. We propose to compare three population-based metaheuristics (genetic algorithm, ant algorithm and particle swarm optimization) with and without the help of a local optimizer. These algorithms make use of solutions that can be explored in three different kinds of search space (a constrained space, a discrete space and a vector space). We study these algorithms from both a theoretical and an experimental perspective: parameter settings are fully studied on a reduced set of data and the performances of algorithms are compared on different sets of real data.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
O. Cappé, Ten years of hmms, http://www.tsi.enst.fr/ cappe/docs/hmmbib.html (March 2001)
A. A. Markov, An example of statistical investigation in the text of “Eugene onyegin” illustrating coupling of “tests” in chains, in: Proceedings of Academic Scienctific St. Petersburg, VI, 1913:153–162
L. E. Baum, J. A. Eagon, An inequality with applications to statistical estimation for probabilistic functions of markov processes to a model for ecology, Bull American Mathematical Society 73 (1967):360–363
A. J. Viterbi, Error bounds for convolutionnal codes and asymptotically optimum decoding algorithm, IEEE Transactions on Information Theory 13 (1967):260–269
L. E. Baum, An inequality and associated maximisation technique in statistical estimation for probabilistic functions of markov processes, Inequalities 3 (1972):1–8
G. D. Forney Jr., The Viterbi algorithm, in: Proceedings of IEEE, Vol. 61, 1973:268–278
T. Brouard, M. Slimane, J. P. Asselin de Beauville, Modélisation des processus simultanés indépendants par chaînes de Markov cachées multidimensionnelles (CMC-MD/I), Tech. Rep. 200, Laboratoire d’Informatique, UniversitéFrançois-Rabelais de Tours (December 1997)
S. Fine, Y. Singer, N. Tishby, The hierarchical hidden markov model: Analysis and applications, Machine Learning 32 (1) (1998):41–62 citeseer.ist.psu.edu/fine98hierarchical.html
L. R. Rabiner, A tutorial on hidden Markov models and selected applications in speech recognition, Proceedings of the IEEE 77 (2) (1989):257–286
S. Aupetit, Contributions aux modèles de Markov cachés: métaheuristiques d’apprentissage, nouveaux modèles et visualisation de dissimilarité, Thèse de doctorat, Laboratoire d’Informatique de l’UniversitéFrançois-Rabelais de Tours, Tours, France (30 November 2005)
H. Bourland, C. Wellekens, Links between Markov models and multiplayer perceptrons, IEEE Transactions on Pattern Analysis and Machine Inteligence 12 (10) (1990):1–4
A. Berchtold, The double chain Markov model, Communications in Statistics: Theory and Methods 28 (11) (1999):2569–2589.
S. R. Eddy, Profile hidden Markov models, Bioinformatics 14 (9) (1998):755–63
Y. Bengio, Markovian models for sequential data, Neural Computing Surveys 2 (1999):129–162
W. Pieczynski, Arbres de Markov Triplet et fusion de Dempster-Shafer, Comptes Rendus de l’Académie des Sciences – Mathématique 336 (10) (2003):869–872
S. Kapadia, Discriminative training of hidden Markov models, Ph.D. Thesis, Downing College, University of Cambridge (18 March 1998)
A. Ganapathiraju, Discriminative techniques in hidden Markov models, Course paper (1999) http://www.isip.msstate.edu/publications/courses/ece_7000_speech/lectures/1999/lecture_11/
M. Berthold, D. J. Hand (Eds), Intelligent Data Analysis: An Introduction, Springer-Verlag, 1998
R. Schluter, W. Macherey, S. Kanthak, H. Ney, L. Welling, Comparison of optimization methods for discriminative training criteria, in: EUROSPEECH ’97, 5th European Conference on Speech Communication and Technology, Rhodes, Greece, 1997:15–18
M. Giurgiu, Maximization of mutual information for training hidden markov models in speech recognition, in: 3rd COST #276 Workshop, Budapest, Hungary, 2002:96–101
K. Vertanen, An overview of discriminative training for speech recognition, Tech. Rep., University of Cambridge (2004)
A. Ljolje, Y. Ephraim, L. R. Rabiner, Estimation of hidden Markov model parameters by minimizing empirical error rate, in: IEEE International Conference on Acoustic, Speech, Signal Processing, Albuquerque, 1990. 709–712 http://ece.gmu.edu/∼yephraim/Papers/icassp 1990 mcehmm.pdf
L. Saul, M. Rahim, Maximum likelihood and minimum classification error factor analysis for automatic speech recognition, IEEE Transactions on Speech and Audio Processing 8 (2) (2000):115–125
B.-H. Juang, L. R. Rabiner, The segmental k-means algorithm for estimating parameters of hidden Markov models, IEEE Transactions on Acoustics, Speech and Signal Processing 38 (9) (1990):1639–1641
R. Dugad, U. B. Desai, A tutorial on hidden Markov models, Tech. Rep. SPANN-96.1, Indian Institute of Technology, Bombay, India (May 1996)
J. Dreo, A. Petrowski, P. Siarry, E. Taillard, Métaheuristiques pour l’optimisation difficile, Eyrolles, Paris, 2003
S. Kirkpatrick, C. D. Gelatt, M. P. Vecchi, Optimizing by simulated annealing, Science 220 (4598) (1983):671–680
F. Glover, Future paths for integer programming and links to artificial intelligence, Computers and Operations Research 13 (1986):533–549
F. Glover, Tabu search – part I, ORSA Journal on Computing 1 (3) (1989):190–206
F. Glover, Tabu search – part II, ORSA Journal on Computing 2 (1) (1989):4–32
A. Hertz, E. Taillard, D. de Werra, A Tutorial on tabu search, in: Proceedings of Giornate di Lavoro AIRO’95 (Enterprise Systems: Management of Technological and Organizational Changes, 1992:13–24
F. Glover, M. Laguna, Tabu Search, Kluwer Academic Publishers, 1997
J. H. Holland, Adaptation in Natural and Artificial Systems, University of Michigan Press: Ann Arbor, MI, 1975
D. E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley, 1989
S. Bulaja, Population-based incremental learning: a method for integrating genetic search based function optimization and competitive learning, Tech. Rep. CMU-CS-94-163, Carnegie Mellon University (1994)
S. Bulaja, R. Caruana, Removing the genetics from the standard genetic algorithm, in: A. Prieditis, S. Russel (Eds.), The International Conference on Machine Learning (ML’95), Morgan Kaufman Publishers, San Mateo, CA, 1995:38–46
N. Monmarché, Algorithmes de fourmis artificielles: applications àla classification et àl’optimisation, Thèse de doctorat, Laboratoire d’Informatique de l’UniversitéFrançois-Rabelais de Tours (20 December 2000)
N. Monmarché, G. Venturini, M. Slimane, On how Pachycondyla apicalis ants suggest a new search algorithm, Future Generation Computer Systems 16 (8) (2000):937–946
J. Kennedy, R. Eberhart, Particle swarm optimization, in: Proceedings of the IEEE International Joint Conference on Neural Networks, Vol. 4, IEEE, 1995:1942–1948
M. Clerc, L’optimisation par essaims particulaires : versions paramétriques et adaptatives, Hermes Science - Lavoisier, Paris, 2005
D. B. Paul, Training of HMM recognizers by simulated annealing, in: Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, 1985:13–16
Y. Hamam, T. Al Ani, Simulated annealing approach for hidden Markov models, in: 4th WG-7.6 Working Conference on Optimization-Based Computer-Aided Modeling and Design, ESIEE, France, 1996
T.-Y. Chen, X.-D. Mei, J.-S. Pan, S.-H. Sun, Optimization of hmm by the tabu search algorithm., Journal Information Science and Engineering 20 (5) (2004):949–957
M. Slimane, T. Brouard, G. Venturini, J.-P. Asselin de Beauville, Apprentissage non-superviséd’images par hybridation génétique d’une chaîne de Markov cachée, Traitement du signal 16 (6) (1999):461–475
R. Thomsen, Evolving the topology of hidden Markov models using evolutionary algorithms, in: Proceedings of Parallel Problem Solving from Nature VII (PPSN-2002), 2002:861–870
B. Maxwell, S. Anderson, Training hidden markov models using population-based learning, in: W. Banzhaf, J. Daida, A. E. Eiben, M. H. Garzon, V. Honavar, M. Jakiela, R. E. Smith (Eds.), Proceedings of the Genetic and Evolutionary Computation Conference (GECCO’99), Vol. 1, Morgan Kaufmann, Orlando, Florida, USA, 1999, p. 944. http://citeseer.ist.psu.edu/maxwell99training.html
S. Aupetit, N. Monmarché, M. Slimane, S. Liardet, An exponential representation in the API algorithm for hidden Markov models training, in: Proceedings of the 7th International Conference on Artificial Evolution (EA’05), Lille, France, 2005, cD-Rom
T. K. Rasmussen, T. Krink, Improved hidden Markov model training for multiple sequence alignment by a particle swarm optimization – evolutionary algorithm hybrid, BioSystems 72 (2003):5–17
S. Aupetit, N. Monmarché, M. Slimane, Apprentissage de modèles de Markov cachés par essaim particulaire, in: J.-C. Billaut, C. Esswein (Eds.), ROADEF’05 : 6ème congrès de la SociétéFrançaise de Recherche Opérationnelle et d’Aide àla Décision, Vol. 1, Presses Universitaire François-Rabelais, Tours, France, 2005:375–391
F. Samaria, A. Harter, Parameterisation of a stochastic model for human face identification, in: IEEE workshop on Applications of Computer Vision, Florida, 1994
T.C. Design, Free Background Textures, Flowers, http://www.tcdesign.net/free_textures_flowers.htm , accessed junuary 2006 (January 2006)
Textures Unlimited, Black & white textures, http://www.geocities.com/texturesunlimited/blackwhite.html, accessed junuary 2006 (January 2006)
S. Agarwal, A. Awan, D. Roth, Learning to detect objects in images via a sparse, part-based representation, IEEE Transactions on Pattern Analysis and Machine Intelligence 26 (11) (2004):1475–1490
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Aupetit, S., Monmarché, N., Slimane, M. (2007). Hidden Markov Models Training Using Population-based Metaheuristics. In: Siarry, P., Michalewicz, Z. (eds) Advances in Metaheuristics for Hard Optimization. Natural Computing Series. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-72960-0_20
Download citation
DOI: https://doi.org/10.1007/978-3-540-72960-0_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-72959-4
Online ISBN: 978-3-540-72960-0
eBook Packages: Computer ScienceComputer Science (R0)