Neural network training acceleration using NVIDIA CUDA technology for image recognition

Abstract


In this paper, an implementation of neural network trained by algorithm based on Levenberg-Marquardt method is presented. Training of neural network increased by almost 9 times using NVIDIA CUDA technology. Implemented neural network is used for the recognition of noised images.

About the authors

Alexander A Fertsev

Mordovian State University by N. P. Ogarev

Email: a.fertsev@rm.volga.rt.ru
каф. прикладной математики; Мордовский государственный университет им. Н. П. Огарева; Mordovian State University by N. P. Ogarev

References

  1. Mashor M. Y., Sulaiman S. N. Recognition of Noisy Numerals using Neural Network // IJCIM, 2001. Vol. 9, no. 3. Pp. 158-164.
  2. Boureau Y.-L., Bach F., LeCun Y., Ponce J. Learning mid-level features for recognition / In: IEEE Conference on Computer Vision and Pattern Recognition, 2010. Pp. 2559-2566.
  3. Hagan M. T., Menhaj M. Training feedforward networks with the Marquardt algorithm // IEEE Transactions on Neural Networks, 1994. Vol. 5, no. 6. Pp. 989-993.
  4. Wilamowski B. M., Chen Y., Malinowski A. Efficient algorithm for training neural networks with one hidden layer / In: International Joint Conference on Neural Networks (IJCNN '99). Vol. 3, 1999. Pp. 1725-1728.
  5. Marquardt D. An Algorithm for Least-Squares Estimation of Nonlinear Parameters // SIAM J. Appl. Math., 1963. Vol. 11, no. 2. Pp. 431-441.
  6. David J. C. MacKay A practical Bayesian framework for backpropagation networks // Neural Computation, 1992. Vol. 4, no. 3. Pp. 448-472.
  7. Poland J. On the Robustness of update strategies for the Bayesian hyperparameter alpha, available on: http://www-alg.ist.hokudai.ac.jp/~jan/alpha.pdf, 2001.
  8. Nguyen D., Widrow B. Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights / In: International Joint Conference on Neural Networks. Vol. 3, 1990. Pp. 21-26.
  9. Изотов П. Ю., Суханов С. В., Головашкин Д. Л. Технология реализации нейросетевого алгоритма в среде CUDA на примере распознавания рукописных цифр // Компьютерная оптика, 2010. Т. 34, № 2. С. 243-252.
  10. Gonzalez R. C., Woods R. E. Digital Image Processing. Boston, MA: Addison-Wesley Publishing Company, 1992. 528 pp.

Statistics

Views

Abstract - 28

PDF (Russian) - 8

Cited-By


Article Metrics

Metrics Loading ...

Refbacks

  • There are currently no refbacks.

Copyright (c) 2012 Samara State Technical University

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.

This website uses cookies

You consent to our cookies if you continue to use our website.

About Cookies