Abstract
The purpose of this work is to further study the relevance of accelerating the Monte-Carlo calculations for the gamma rays external radiotherapy through feed-forward neural networks. We have previously presented a parallel incremental algorithm that builds neural networks of reduced size, while providing high quality approximations of the dose deposit [4]. Our parallel algorithm consists in an optimized decomposition of the initial learning dataset (also called learning domain) in as much subsets as available processors. However, although that decomposition provides subsets of similar signal complexities, their sizes may be quite different, still implying potential differences in their learning times. This paper presents an efficient data extraction allowing a good and balanced training without any loss of signal information. As will be shown, the resulting irregular decomposition permits an important improvement in the learning time of the global network.
Keywords
- Pre-clinical studies
- Doses Distributions
- Neural Networks
- Learning algorithms
- External radiotherapy
- Data extraction
Download conference paper PDF
References
Bahi, J.M., Contassot-Vivier, S., Makovicka, L., Martin, E., Sauget, M.: Neurad. Agence pour la Protection des Programmes. No: IDDN.FR.001.130035.000.S.P.2006.000.10000 (2006)
Bahi, J.M., Contassot-Vivier, S., Makovicka, L., Martin, É., Sauget, M.: Neural network based algorithm for radiation dose evaluation in heterogeneous environments. In: Kollias, S.D., Stafylopatis, A., Duch, W., Oja, E. (eds.) ICANN 2006. LNCS, vol. 4132, pp. 777–787. Springer, Heidelberg (2006)
Bahi, J.M., Contassot-Vivier, S., Sauget, M.: An incremental learning algorithm for functional approximation. Advances in Engineering Software 40(8), 725–730 (2009), doi:10.1016/j.advengsoft.2008.12.018
Bahi, J.M., Contassot-Vivier, S., Sauget, M., Vasseur, A.: A parallel incremental learning algorithm for neural networks with fault tolerance. In: Palma, J.M.L.M., Amestoy, P., Daydé, M.J., Mattoso, M., Lopes, J.C. (eds.) VECPAR 2008. LNCS, vol. 5336, pp. 174–187. Springer, Heidelberg (2008)
BEAM-nrc: NRC of Canada, http://www.irs.inms.nrc.ca/BEAM/beamhome.html
Blake, S.W.: Artificial neural network modelling of megavoltage photon dose distributions. Physics in Medicine and Biology 49, 2515–2526 (2004)
Chu, C.K., Deng, W.S.: An interpolation method for adapting to sparse design in multivariate nonparametric regression. Journal of Statistical Planning and Inference 116(1), 91–111 (2003)
Grochowski, M., Jankowski, N.: Comparison of instance selection algorithms ii. results and comments. In: Rutkowski, et al. [16], pp. 580–585
Guo, G., Zhang, J.S., Zhang, G.Y.: A method to sparsify the solution of support vector regression. Neural Comput. Appl. 19(1), 115–122 (2010)
Haas, O., Goodband, J.: Artificial Neural Networks in Radiation Therapy. In: Intelligent and Adaptive Systems in Medicine. Series in Medical Physics and Biomedical Engineering, pp. 213–258. Taylor & Francis, Abington (2008)
Jankowski, N., Grochowski, M.: Comparison of instances seletion algorithms i. algorithms survey. In: Rutkowski, et al. [16], pp. 598–603
Makovicka, L., Vasseur, A., Sauget, M., Martin, E., Gschwind, R., Henriet, J., Salomon, M.: Avenir des nouveaux concepts des calculs dosimétriques basés sur les méthodes de Monte Carlo. Radioprotection 44(1), 77–88 (2009), http://dx.doi.org/10.1051/radiopro/2008055
Computing Mesocenter of Franche-Comté, http://meso.univ-fcomte.fr
Open Source High Performance Computing, http://www.open-mpi.org
Pan, F., Wang, W.: Finding representative set from massive data. Tech. rep., IEEE International Conference on Data Mining (2005)
Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds.): ICAISC 2004. LNCS (LNAI), vol. 3070. Springer, Heidelberg (2004)
Sauget, M., Laurent, R., Henriet, J., Salomon, M., Gschwind, R., Contassot-Vivier, S., Makovicka, L., Soussen, C.: Efficient domain decomposition for a neural network learning algorithm, used for the dose evaluation in external radiotherapy. In: Diamantaras, K.I., Duch, W., Iliadis, L.S. (eds.) ICANN 2010, Part I. LNCS, vol. 6352, pp. 261–266. Springer, Heidelberg (2010)
Vasseur, A., Makovicka, L., Martin, E., Sauget, M., Contassot-Vivier, S., Bahi, J.M.: Dose calculations using artificial neural networks: a feasibility study for photon beams. Nucl. Instr. and Meth. in Phys. Res. B 266(7), 1085–1093 (2008)
Wu, A., Hsieh, W.W., Tang, B.: Neural network forecasts of the tropical pacific sea surface temperatures. Neural Networks 19(2), 145–154 (2006), earth Sciences and Environmental Applications of Computational Intelligence
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 International Federation for Information Processing
About this paper
Cite this paper
Sauget, M., Henriet, J., Salomon, M., Contassot-Vivier, S. (2011). Large Datasets: A Mixed Method to Adapt and Improve Their Learning by Neural Networks Used in Regression Contexts. In: Iliadis, L., Jayne, C. (eds) Engineering Applications of Neural Networks. EANN AIAI 2011 2011. IFIP Advances in Information and Communication Technology, vol 363. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23957-1_21
Download citation
DOI: https://doi.org/10.1007/978-3-642-23957-1_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23956-4
Online ISBN: 978-3-642-23957-1
eBook Packages: Computer ScienceComputer Science (R0)