Abstract
With growth of data sets, the efficiency of Extreme Learning Machine (ELM) model combined with accustomed hardware implementation such as Field-programmable gate array (FPGA) became attractive for many real-time learning tasks. In order to reduce resource occupation in eventual trained model on FPGA, it is more efficient to store fixed-point data rather than double-floating data in the on-chip RAMs. This paper conducts the fixed-point evaluation of ELM for classification. We converted the ELM algorithm into a fixed-point version by changing the operation type, approximating the complex function and blocking the large-scale matrixes, according to the architecture ELM would be implemented on FPGA. The performance of classification with single bit-width and mixed bit-width were evaluated respectively. Experimental results show that the fixed-point representation used on ELM does work for some application, while the performance could be better if we adopt mixed bit-width.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amin, H., Curtis, K., Hayes Gill, B.: Piecewise linear approximation applied to nonlinear function of a neural network. IEE Proc. Circuits Devices Syst. 144(6), 313–317 (1997)
Courbariaux, M. Bengio, Y. David, J.P.: Low precision storage for deep learning. C. Eprint Arxiv (2014)
Decherchi, S., Gastaldo, P., Leoncini, A., et al.: Efficient digital implementation of extreme learning machines for classification. IEEE Trans. J. Circuits Syst. II: Express. Briefs 59(8), 496–500 (2012)
Hoerl, A.E., Kennard, R.W.: Ridge regression: biased estimation for nonorthogonal problems. J. Technometrics 12(1), 55–67 (2012)
Huang, G.B., Zhou, H., Ding, X., et al.: Identification of common molecular subsequences. IEEE Trans. J. Syst. Man Cybern. Part B: Cybern. 42(2), 513–529 (2012)
Jiang, J., Hu, R., Zhang, F., et al.: Experimental demonstration of the fixed-point sparse coding performance. J. Cybern. Inform. Technol. 14(5), 40–50 (2014)
Jie, Z.: Fine-grained algorithm and architecture for data processing in SAR applications (in Chinese). University of Defense and Technology (2010)
van Heeswijk, M., Miche, Y., Oja, E., et al.: GPU-accelerated and parallelized ELM ensembles for large-scale regression. J. Neurocomput. 74(16), 2430–2437 (2011)
Vanhoucke, V., Senior, A., Mao, M.Z.: Improving the speed of neural networks on CPUs. In: Proceedings of Deep Learning and Unsupervised Feature Learning Workshop Nips (2011)
Acknowledgments
This work is funded by National Science Foundation of China(number 61303070).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Xu, Y., Jiang, J., Jiang, J., Liu, Z., Xu, J. (2016). Fixed-Point Evaluation of Extreme Learning Machine for Classification. In: Cao, J., Mao, K., Wu, J., Lendasse, A. (eds) Proceedings of ELM-2015 Volume 1. Proceedings in Adaptation, Learning and Optimization, vol 6. Springer, Cham. https://doi.org/10.1007/978-3-319-28397-5_3
Download citation
DOI: https://doi.org/10.1007/978-3-319-28397-5_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-28396-8
Online ISBN: 978-3-319-28397-5
eBook Packages: EngineeringEngineering (R0)