Abstract
In this paper we are concerned with learning models of actions and compare a purely generative model based on Hidden Markov Models to a discriminatively trained recurrent LSTM network in terms of their properties and their suitability to learn and represent models of actions. Specifically we compare the performance of the two models regarding the overall classification accuracy, the amount of training sequences required and how early in the progression of a sequence they are able to correctly classify the corresponding sequence. We show that, despite the current trend towards (deep) neural networks, traditional graphical model approaches are still beneficial under conditions where only few data points or limited computing power is available.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Sugiura, K., Iwahashi, N., Kashioka, H., Nakamura, S.: Learning, generation and recognition of motions by reference-point-dependent probabilistic models. Adv. Robot. 25(6–7), 825–848 (2011)
Tenorth, M., Beetz, M.: KnowRob - knowledge processing for autonomous personal robots. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 4261–4266 (2009)
Panzner, M., Beyer, O., Cimiano, P.: Human activity classification with online growing neural gas. In: Workshop on New Challenges in Neural Computation (NC2) (2013)
Veeriah, V., Zhuang, N., Qi, G.-J.: Differential recurrent neural networks for action recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4041–4049 (2015)
Rabiner, L., Juang, B.: An introduction to hidden Markov models. IEEE ASSP Mag. 3(1), 4–16 (1986)
Weghe, N., Kuijpers, B., Bogaert, P., Maeyer, P.: A qualitative trajectory calculus and the composition of its relations. In: RodrÃguez, M.A., Cruz, I., Levashkin, S., Egenhofer, M.J. (eds.) GeoS 2005. LNCS, vol. 3799, pp. 60–76. Springer, Heidelberg (2005). doi:10.1007/11586180_5
Bruss, T., Rüschendorf, L.: On the perception of time. Gerontology 56(4), 361–370 (2010)
Omohundro, S.: Best-first model merging for dynamic learning and recognition. In: Advances in Neural Information Processing Systems 4, pp. 958–965. Morgan Kaufmann (1992)
Stolcke, A., Omohundro, S.: Inducing probabilistic grammars by Bayesian model merging. In: Carrasco, R.C., Oncina, J. (eds.) ICGI 1994. LNCS, vol. 862, pp. 106–118. Springer, Heidelberg (1994). doi:10.1007/3-540-58473-0_141
Shepard, R.N.: Toward a universal law of generalization for psychological science. Science 237(4820), 1317–1323 (1987)
Panzner, M., Cimiano, P.: Incremental learning of action models as HMMs over qualitative trajectory representations. In: Workshop on New Challenges in Neural Computation (NC2) (2015). http://pub.uni-bielefeld.de/publication/2775414
Greff, K., Srivastava, R.K., KoutnÃk, J., Steunebrink, B.R., Schmidhuber, J.: LSTM: a search space odyssey. arXiv preprint arXiv:1503.04069 (2015)
Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: continual prediction with LSTM. Neural Comput. 12(10), 2451–2471 (2000)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Tieleman, T., Hinton, G.: Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. COURSERA: Neural Netw. Mach. Learn. 4, 2 (2012)
Panzner, M., Gaspers, J., Cimiano, P.: Learning linguistic constructions grounded in qualitative action models. In: IEEE International Symposium on Robot and Human Interactive Communication (2015). http://pub.uni-bielefeld.de/publication/2733058
Panzner, M.: TLS Dataset (2016). doi:10.4119/unibi/2904362
Acknowledgement
This research/work was supported by the Cluster of Excellence Cognitive Interaction Technology ‘CITEC’ (EXC 277) at Bielefeld University, which is funded by the German Research Foundation (DFG).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Panzner, M., Cimiano, P. (2016). Comparing Hidden Markov Models and Long Short Term Memory Neural Networks for Learning Action Representations. In: Pardalos, P., Conca, P., Giuffrida, G., Nicosia, G. (eds) Machine Learning, Optimization, and Big Data. MOD 2016. Lecture Notes in Computer Science(), vol 10122. Springer, Cham. https://doi.org/10.1007/978-3-319-51469-7_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-51469-7_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-51468-0
Online ISBN: 978-3-319-51469-7
eBook Packages: Computer ScienceComputer Science (R0)