Abstract
This paper proposes an algorithmic optimization for the feature extractors of biologically inspired Convolutional Neural Networks (CNNs). CNNs are successfully used for different visual pattern recognition applications such as OCR, face detection and object classification. These applications require complex networks exceeding 100,000 interconnected computational nodes. To reduce the computational complexity a modified algorithm is proposed; real benchmarks show 65 - 83% reduction, with equal or even better recognition accuracy. Exploiting the available parallelism in CNNs is essential to reduce the computational scaling problems. Therefore the modified version of the algorithm is implemented and evaluated on a GPU platform to demonstrate the suitability on a cost effective parallel platform. A speedup of 2.5x with respect to the standard algorithm is achieved.
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
Chakradhar, S., Sankaradas, M., Jakkula, V., Cadambi, S.: A dynamically configurable coprocessor for convolutional neural networks. In: ISCA 2010: Proceedings of the 37th Annual International Symposium on Computer Architecture, pp. 247–257. ACM, New York (2010)
Farabet, C., Poulet, C., Han, J., LeCun, Y.: Cnp: An fpga-based processor for convolutional networks. In: International Conference on Field Programmable Logic and Applications, FPL 2009, pp. 32–37 (August 2009)
Garcia, C., Delakis, M.: Convolutional face finder: A neural architecture for fast and robust face detection. IEEE Trans. Pattern Anal. Mach. Intell. 26(11), 1408–1423 (2004)
Haykin, S.: Neural Networks and Learning Machines, 3rd edn. Prentice Hall, Englewood Cliffs (2008)
Hinton, G.E.: Connectionist learning procedures. Artif. Intell. 40(1-3), 185–234 (1989)
LeCun, Y., Boser, B., Denker, J.S., Henderson, D., Howard, R.E., Hubbard, W., Jackel, L.D.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989)
Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proceedings of the IEEE 86(11), 2278–2324 (1998)
Lecun, Y., Huang, F.J., Bottou, L.: Learning methods for generic object recognition with invariance to pose and lighting. In: In Proceedings of CVPR 2004 (2004)
Nixon, M., Aguado, A.S.: Feature Extraction & Image Processing, 2nd edn. Academic Press, London (2008)
Nvidia: NVIDIA CUDA C Programming Guide 3.2. NVIDIA Corporation (2010)
Peemen, M., Mesman, B., Corporaal, C.: Speed sign detection and recognition by convolutional neural networks. In: Proceedings of the 8th International Automotive Congress, pp. 162–170 (2011)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. In: Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1, pp. 318–362. MIT Press, Cambridge (1986)
Simard, P., Steinkraus, D., Platt, J.C.: Best practices for convolutional neural networks applied to visual document analysis. In: ICDAR, pp. 958–962 (2003)
Szarvas, M., Yoshizawa, A., Yamamoto, M., Ogata, J.: Pedestrian detection with convolutional neural networks. In: Proceedings IEEE Intelligent Vehicles Symposium, Las Vegas, NV, pp. 224–229 (June 2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Peemen, M., Mesman, B., Corporaal, H. (2011). Efficiency Optimization of Trainable Feature Extractors for a Consumer Platform. In: Blanc-Talon, J., Kleihorst, R., Philips, W., Popescu, D., Scheunders, P. (eds) Advanced Concepts for Intelligent Vision Systems. ACIVS 2011. Lecture Notes in Computer Science, vol 6915. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-23687-7_27
Download citation
DOI: https://doi.org/10.1007/978-3-642-23687-7_27
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-23686-0
Online ISBN: 978-3-642-23687-7
eBook Packages: Computer ScienceComputer Science (R0)