Advertisement

Minimizing Computation in Convolutional Neural Networks

  • Jason Cong
  • Bingjun Xiao
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8681)

Abstract

Convolutional Neural Networks (CNNs) have been successfully used for many computer vision applications. It would be beneficial to these applications if the computational workload of CNNs could be reduced. In this work we analyze the linear algebraic properties of CNNs and propose an algorithmic modification to reduce their computational workload. An up to a 47% reduction can be achieved without any change in the image recognition results or the addition of any hardware accelerators.

Keywords

Convolutional Neural Network Convolution Kernel Hardware Accelerator Computer Vision Application Matrix Partitioning 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
  2. 2.
    Behnke, S.: Hierarchical Neural Networks for Image Interpretation. LNCS, vol. 2766. Springer, Heidelberg (2003)zbMATHGoogle Scholar
  3. 3.
    Chakradhar, S., Sankaradas, M., Jakkula, V., Cadambi, S.: A dynamically configurable coprocessor for convolutional neural networks. In: International Symposium on Computer Architecture, p. 247 (2010)Google Scholar
  4. 4.
    Chellapilla, K., Puri, S., Simard, P.: High Performance Convolutional Neural Networks for Document Processing. In: International Workshop on Frontiers in Handwriting Recognition (2006)Google Scholar
  5. 5.
    Farabet, C., Poulet, C., Han, J.Y., LeCun, Y.: CNP: An FPGA-based processor for Convolutional Networks. In: International Conference on Field Programmable Logic and Applications, vol. 1, pp. 32–37 (August 2009)Google Scholar
  6. 6.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet Classification with Deep Convolutional Neural Networks. In: Proceedings of Neural Information and Processing Systems, pp. 1–9 (2012)Google Scholar
  7. 7.
    Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86, 2278–2324 (1998)CrossRefGoogle Scholar
  8. 8.
    Osadchy, M., Yann, L.C., Matthew, L.M.: Synergistic Face Detection and Pose Estimation with Energy-Based Models. Journal of Machine Learning Research 8, 1197–1215 (2007)Google Scholar
  9. 9.
    Peemen, M., Setio, A.A.A., Mesman, B., Corporaal, H.: Memory-centric accelerator design for Convolutional Neural Networks. In: International Conference on Computer Design, pp. 13–19 (October 2013)Google Scholar
  10. 10.
    Simard, P., Steinkraus, D., Platt, J.: Best practices for convolutional neural networks applied to visual document analysis. In: International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 958–963 (2003)Google Scholar
  11. 11.
    Strassen, V.: Gaussian elimination is not optimal. Numerische Mathematik 13(4), 354–356 (1969)CrossRefzbMATHMathSciNetGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Jason Cong
    • 1
  • Bingjun Xiao
    • 1
  1. 1.Computer Science DepartmentUniversity of CaliforniaLos AngelesUSA

Personalised recommendations