Abstract
The development of parallel batch pattern back propagation training algorithm of multilayer perceptron with two hidden layers and the research of its parallelization efficiency on many-core system are presented in this paper. The model of multilayer perceptron and batch pattern training algorithm are theoretically described. The algorithmic description of the parallel batch pattern training method is presented. Our results show high parallelization efficiency of the developed algorithm on many-core parallel system with 48 CPUs using MPI technology.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Haykin, S.: Neural Networks and Learning Machines, 3rd edn., p. 936. Prentice Hall (2008)
De Llano, R.M., Bosque, J.L.: Study of neural net training methods in parallel and distributed architectures. Future Generation Computer Systems 26(2), 183–190 (2010)
Čerňanský, M.: Training recurrent neural network using multistream extended Kalman filter on multicore processor and CUDA enabled GPU. In: Alippi, C., Polycarpou, M., Panayiotou, C., Ellinas, G. (eds.) ICANN 2009, Part I. LNCS, vol. 5768, pp. 381–390. Springer, Heidelberg (2009)
Lotrič, U., Dobnikar, A.: Parallel implementations of recurrent neural network learning. In: Kolehmainen, M., Toivanen, P., Beliczynski, B. (eds.) ICANNGA 2009. LNCS, vol. 5495, pp. 99–108. Springer, Heidelberg (2009)
http://uweb.deis.unical.it/turchenko/research-projects/pagalinnet/
Turchenko, V., Grandinetti, L.: Scalability of enhanced parallel batch pattern BP training algorithm on general-purpose supercomputers. In: de Leon F. de Carvalho, A.P., Rodríguez-González, S., De Paz Santana, J.F., Rodríguez, J.M.C. (eds.) Distributed Computing and Artificial Intelligence. AISC, vol. 79, pp. 525–532. Springer, Heidelberg (2010)
Turchenko, V., Grandinetti, L.: Parallel batch pattern BP training algorithm of recurrent neural network. In: Proc. 14th IEEE Intern. Conf. on Intelligen. Engin. Syst., Spain, pp. 25–30 (2010)
Turchenko, V., Bosilca, G., Bouteiller, A., Dongarra, J.: Efficient Parallelization of Batch Pattern Training Algorithm on Many-core and Cluster Architectures. In: Proceedings of the 7th IEEE International Conference IDAACS 2013, Germany, pp. 692–698 (2013)
Turchenko, V., Golovko, V., Sachenko, A.: Parallel training algorithm for radial basis function neural network. In: Proceedings of the 7th ICNNAI, Belarus, pp. 47–51 (2012)
Funahashi, K.: On the approximate realization of continuous mappings by neural network. Neural Networks 2, 183–192 (1989)
Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Networks 2, 359–366 (1989)
Sontag, E.: Feedback stabilization using two-hidden-layer nets. IEEE Transactions on Neural Networks 3, 981–990 (1992)
Golovko, V., Galushkin, A.: Neural Networks: Training, Models and Applications, Moscow, Radiotechnika (2001) (in Russian)
Turchenko, V., Grandinetti, L., Bosilca, G., Dongarra, J.: Improvement of parallelization efficiency of batch pattern BP training algorithm using Open MPI. Procedia Computer Science 1(1), 525–533 (2010)
Turchenko, V., Grandinetti, L., Sachenko, A.: Parallel batch pattern training of neural networks on computational clusters. In: Proc. of the 2012 Intern. Conf. HPCS 2012, Spain, pp. 202–208 (2012)
Turchenko, V., Grandinetti, L.: Application of BSP-based computational cost model to predict parallelization efficiency of MLP training algorithm. In: Diamantaras, K., Duch, W., Iliadis, L.S. (eds.) ICANN 2010, Part III. LNCS, vol. 6354, pp. 327–332. Springer, Heidelberg (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Turchenko, V. (2014). Parallel Batch Pattern Training Algorithm for MLP with Two Hidden Layers on Many-Core System. In: Omatu, S., Bersini, H., Corchado, J., Rodríguez, S., Pawlewski, P., Bucciarelli, E. (eds) Distributed Computing and Artificial Intelligence, 11th International Conference. Advances in Intelligent Systems and Computing, vol 290. Springer, Cham. https://doi.org/10.1007/978-3-319-07593-8_62
Download citation
DOI: https://doi.org/10.1007/978-3-319-07593-8_62
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-07592-1
Online ISBN: 978-3-319-07593-8
eBook Packages: EngineeringEngineering (R0)