Abstract
Haptic perception is to identify different targets from haptic input. Haptic data have two prominent features: sequentially real-time and temporally correlated, which calls for a fixed-budget and recurrent perception procedure. Based on an efficient-robust spatio-temporal feature representation, we handle the problem with a bounded online-sequential learning framework (MBS-ESN), and incorporates the strength of batch-regularization bootstrapping, bounded recursive reservoir, and momentum-based estimation. Experimental evaluations show that it outperforms the state-of-the-art methods by a large margin on test accuracy; and its training performance is superior to most compared models from aspects of computational complexity and storage efficiency.
References
Atiya, A.F., Parlos, A.G.: New results on recurrent network training: unifying the algorithms and accelerating convergence. IEEE Trans. Neural Netw. 11(3), 697ā709 (2000)
Bekiroglu, Y., Kragic, D., Kyrki, V.: Learning grasp stability based on tactile data and HMMs. In: Proceedings of 19th International Conference on RO-MAN, pp. 132ā137. IEEE, Viareggio (2010)
Bekiroglu, Y., Laaksonen, J., Jorgensen, J.A., Kyrki, V., Kragic, D.: Assessing grasp stability based on learning and haptic data. IEEE Trans. Robot. 27(3), 616ā629 (2011)
Cao, L., Kotagiri, R., Sun, F., Li, H., Huang, W., Aye, Z.M.M.: Efficient spatio-temporal tactile object recognition with randomized tiling convolutional networks in a hierarchical fusion strategy. In: Proceedings of 30th AAAI, pp. 3337ā3345. AAAI Press, Phoenix (2016)
Chong, E.K., Zak, S.H.: An Introduction to Optimization, vol. 76. Wiley, Hoboken (2013)
CsatĆ³, L., Opper, M.: Sparse on-line Gaussian processes. Neural Comput. 14(3), 641ā668 (2002)
Drimus, A., Kootstra, G., Bilberg, A., Kragic, D.: Design of a flexible tactile sensor for classification of rigid and deformable objects. Robot. Auton. Syst. 62(1), 3ā15 (2014)
Farhang-Boroujeny, B.: Adaptive Filters: Theory and Applications. Wiley, Hoboken (2013)
Hinton, G.E.: A practical guide to training restricted Boltzmann machines. In: Montavon, G., Orr, G.B., MĆ¼ller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, 2nd edn, pp. 599ā619. Springer, Heidelberg (2012). doi:10.1007/978-3-642-35289-8_32
Hoerl, A.E., Kennard, R.W.: Ridge regression: biased estimation for nonorthogonal problems. Technometrics 12(1), 55ā67 (1970)
Horn, B.K., Schunck, B.G.: Determining optical flow. Artif. Intell. 17, 185ā203 (1981)
Jaeger, H.: Adaptive nonlinear system identification with echo state networks. In: Advances in Neural Information Processing Systems, pp. 593ā600 (2002)
Jaeger, H., Haas, H.: Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304(5667), 78ā80 (2004)
Kountouriotis, P., Obradovic, D., Goh, S.L., Mandic, D.P.: Multi-step forecasting using echo state networks. In: International Conference on Computer as a Tool, EUROCON 2005, vol. 2, pp. 1574ā1577. IEEE (2005)
Liang, N.Y., Huang, G.B., Saratchandran, P., Sundararajan, N.: A fast and accurate online sequential learning algorithm for feedforward networks. IEEE Trans. Neural Netw. 17(6), 1411ā1423 (2006)
LukoÅ”EviÄIus, M., Jaeger, H.: Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3(3), 127ā149 (2009)
Maass, W., NatschlƤger, T., Markram, H.: Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput. 14(11), 2531ā2560 (2002)
Neal, R.M.: Bayesian Learning for Neural Networks, vol. 118. Springer Science & Business Media, New York (2012). doi:10.1007/978-1-4612-0745-0
Orabona, F., Castellini, C., Caputo, B., Jie, L., Sandini, G.: On-line independent support vector machines. Pattern Recogn. 43(4), 1402ā1412 (2010)
Orabona, F., Keshet, J., Caputo, B.: Bounded kernel-based online learning. J. Mach. Learn. Res. 10, 2643ā2666 (2009)
Rao, C.R., Mitra, S.K.: Generalized Inverse of Matrices and Its Applications, vol. 7. Wiley, New York (1971)
Shi, Z., Han, M.: Support vector echo-state machine for chaotic time-series prediction. IEEE Trans. Neural Netw. 18(2), 359ā372 (2007)
Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Advances in Neural Information Processing Systems, pp. 568ā576 (2014)
Soh, H., Demiris, Y.: Incrementally learning objects by touch: online discriminative and generative models for tactile-based recognition. IEEE Trans. Haptics 7(4), 512 (2014)
Soh, H., Su, Y., Demiris, Y.: Online spatio-temporal Gaussian process experts with application to tactile classification. In: Proceedings of 25th IROS, pp. 4489ā4496. IEEE/RSJ, Algarve (2012)
Soh, H., Demiris, Y.: Iterative temporal learning and prediction with the sparse online echo state Gaussian process. In: Proceedings of 25th IJCNN, pp. 1ā8. IEEE, Brisbane (2012)
Soh, H., Demiris, Y.: Spatio-temporal learning with the online finite and infinite echo-state Gaussian processes. IEEE Trans. Neural Netw. Learn. Syst. 26(3), 522ā536 (2015)
Van Vaerenbergh, S., SantamarĆa, I., Liu, W., PrĆncipe, J.C.: Fixed-budget kernel recursive least-squares. In: 2010 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), pp. 1882ā1885. IEEE (2010)
Wang, Z., Crammer, K., Vucetic, S.: Breaking the curse of kernelization: budgeted stochastic gradient descent for large-scale SVM training. J. Mach. Learn. Res. 13(1), 3103ā3131 (2012)
Yang, J., Liu, H., Sun, F., Gao, M.: Tactile sequence classification using joint kernel sparse coding. In: Proceedings of 28th IJCNN, pp. 1ā6. IEEE, Killarney (2015)
Acknowledgments
This work is supported by National Natural Science Foundation of China with grant number 041320190.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2017 Springer International Publishing AG
About this paper
Cite this paper
Cao, L., Sun, F., Liu, X., Huang, W., Cheng, W., Kotagiri, R. (2017). Fix-Budget and Recurrent Data Mining forĀ Online Haptic Perception. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, ES. (eds) Neural Information Processing. ICONIP 2017. Lecture Notes in Computer Science(), vol 10638. Springer, Cham. https://doi.org/10.1007/978-3-319-70139-4_59
Download citation
DOI: https://doi.org/10.1007/978-3-319-70139-4_59
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-70138-7
Online ISBN: 978-3-319-70139-4
eBook Packages: Computer ScienceComputer Science (R0)