Graphics Processing Units (GPUs) can provide remarkable performance gains when compared to CPUs for computationally-intensive applications. Thus they are much attractive to be used as dedicated hardware in many fields such as in machine learning. In particular, the implementation of neural networks (NNs) in GPUs can decrease enormously the long training times during the learning process. In this paper, we describe a parallel implementation of the Multiple Back-Propagation (MBP) algorithm and present the results obtained when running the algorithm on two well-known benchmarks. We show that for both classification and regression problems our implementation reduces the computational cost when compared with the standalone CPU version.
10th International Conference on Intelligent Data Engineering and Automated Learning - IDEAL 2009, September 2009
DOI
Cited by
Year 2015 : 3 citations
Wang, Y., Tang, P., An, H., Liu, Z., Wang, K., & Zhou, Y. (2015, November). Optimization and Analysis of Parallel Back Propagation Neural Network on GPU Using CUDA. In Neural Information Processing (pp. 156-163). Springer International Publishing.
Li, B., & Liu, C. (2015, August). Parallel BP Neural Network on Single-chip Cloud Computer. In High Performance Computing and Communications (HPCC), 2015 IEEE 7th International Symposium on Cyberspace Safety and Security (CSS), 2015 IEEE 12th International Conference on Embedded Software and Systems (ICESS), 2015 IEEE 17th International Conference on (pp. 1871-1875). IEEE.
K.Karthikeyan, Sayantani Basu. Neural Network Technique in Data Mining for Prediction of Earth Quake. International Journal Of Pharmacy & Technology. Vol. 7, Issue 3, pp. 9543-9554 (2015)
Year 2014 : 3 citations
Beam, Andrew L., Alison Motsinger-Reif, and Jon Doyle. "Bayesian neural networks for detecting epistasis in genetic association studies." BMC bioinformatics 15.1 (2014): 368.
Horita, Tadayoshi, et al. "A GPGPU-Based Acceleration of Fault-Tolerant MLP Learnings." Embedded Multicore/Manycore SoCs (MCSoc), 2014 IEEE 8th International Symposium on. IEEE, 2014.
Beam, Andrew L., Alison Motsinger-Reif, and Jon Doyle. "Bayesian Neural Networks for Genetic Association Studies of Complex Disease." arXiv preprint arXiv:1404.3989 (2014).
Year 2013 : 3 citations
Baptista, Darío, and Fernando Morgado-Dias. "A survey of artificial neural network training tools." Neural Computing and Applications 23.3-4 (2013): 609-615.
Kahandawa, G. C., et al. "Use of fixed wavelength fibre-bragg grating (FBG) filters to capture time domain data from the distorted spectrum of an embedded FBG sensor to estimate strain with an artificial neural network." Sensors and Actuators A: Physical 194 (2013): 1-7.
Kahandawa, Gayan C., et al. "Prediction of obsolete FBG sensor using ANN for efficient and robust operation of SHM systems." Key Engineering Materials 558 (2013): 546-553.
Year 2012 : 6 citations
Ole-Christoffer Granmo. Short-term forecasting of electricity consumption using Gaussian processes. Master’s thesis, University of Agder, 2012.
Zhang Branch, Yang Bo , Wang Lin , and Zhu Fuxiang "Modern parallel GPU-based optimization algorithm". Computer Science 39, no 4 (2012), 304-310.
Yi Wu Zheng and Behandish Morad. Real-time pump scheduling using genetic algorithm and artificial neural network based on graphics processing unit. In 14th Water Distribution Systems Analysis Conference (WDSA 2012), 2012.
Yi Wu Zheng and Behandish Morad. Comparing methods of parallel genetic optimization for pump scheduling using hydraulic model and GPU-based ANN metamodel. In 14th Water Distribution Systems Analysis Conference (WDSA 2012), 2012.
Pavel Krömer, Emilio Corchado, Václav Snášel, Jan Platoš, and Laura García-Hernández. Neural PCA and maximum likelihood hebbian learning on the GPU. In Artificial Neural Networks and Machine Learning (ICANN 2012), LNCS 7553, pages 132–139, 2012.
Andréa Martiniano da Silva. Aplicação de técnica da mineração de dados na identificação do perfil de empregados absenteístas e presenteístas em uma empresa de courier da cidade de são paulo. Master’s thesis, Universidade Nove de Julho – UNINOVE, 2012.
Year 2011 : 6 citations
Jarno Mielikainena, Bormin Huanga, Allen H.-L. Huanga, and Mitchell D. Goldbergb. Development of the GPU-based stony-brook university 5-class microphysics scheme in the weather research and forecasting model. J. Proceedings of the SPIE, High-Performance Computing in Remote Sensing, 8183(2):81830V–1–81830V–10, 2011.
Roli Pradhan, K. K. Pathak, and V. P. Singh. Application of neural network in prediction of nancial viability. International Journal of Soft Computing and Engineering (IJSCE), 1(2):41-45, 2011.
Laurentiu Bucur. Sparse Kernel Machines and High Performance Computing. PhD thesis, Faculty of Automatic Control and Computers, University Politehnica of Bucharest, 2011.
Boonkiatpong, Kritsanatt, and Sukree Sinthupinyo. "Applying Multiple Neural Networks on Large Scale Data." Proceedings of International Conference on Information and Electronics Engineering (ICIEE 2011). 2011.
S. A. Zapryagaev and A. A. Karpushin. Calculation and learning artificial neural networks direct distribution by GPUs. VSU HERALD SERIES: System Analysis and Information Technologies, (1):157-164, 2011.
Li Liang. Parallel implementations of hopefield neural networks on GPU. Technical report, DUMAS, Grenoble Universites, 2011.
