Abstract
Prototype learning is widely used in character recognition field. Unfortunately, current learning algorithms require intensive computation burden for large category applications, such as Japanese/Chinese character recognition. To resolve this challenge, a principled parallel method is proposed on GPUs instead of CPUs. We have implemented the method in mini-batch manner as well as stochastic gradient descent (SGD) manner. Our evaluations on a Chinese character database show that our method posses a high scalability while preserving its performance precision. Up to 194X speedup can be achieved in the case of mini-batch. Even to the more difficult SGD occasion, a more than 30-fold speedup is observed.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Liu, C., Nakagawa, M.: Evaluation of prototype learning algorithms for nearest-neighbor classifier in application to handwritten character recognition. Pattern Recognition 34, 601–615 (2001)
Su, T., Liu, C., Zhang, X.: Perceptron learning of modified quadratic discriminant function. In: ICDAR (2011)
Lv, Y., Huang, L., et al.: Learning-Based Candidate Segmentation Scoring for Real-Time Recognition of Online Overlaid Chinese Handwriting. In: ICDAR (2013)
Su, T., Ma, P., et al.: Exploring MPE/MWE Training for Chinese Handwriting Recognition. In: ICDAR (2013)
Zhou, M., Yin, F., Liu, C.: GPU-Based Fast Training of Discriminative Learning Quadratic Discriminant Function for Handwritten Chinese Character Recognition. In: ICDAR (2013)
Raina, R., Madhavan, A., Ng, A.Y.: Large-scale deep unsupervised learning using graphics processors. In: ICML (2009)
Ciresan, D.C., Meier, U., et al.: Deep, big, simple neural nets for handwritten digit recognition. Neural Computation 22, 3207–3220 (2010)
Sato, A., Yamada, K.: Generalized learning vector quantization. In: NIPS (1996)
Wilt, N.: The CUDA Handbook: A Comprehensive Guide to GPU Programming. Addison-Wesley (2013)
Kirk, D.B., Wen-mei, W.H.: Programming massively parallel processors: a hands-on approach. Morgan Kaufmann (2010)
Liu, C., Yin, F., et al.: CASIA Online and Offline Chinese Handwriting Databases. In: ICDAR (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Su, T., Li, S., Ma, P., Deng, S., Liang, G. (2014). Scalable Prototype Learning Using GPUs. In: Campilho, A., Kamel, M. (eds) Image Analysis and Recognition. ICIAR 2014. Lecture Notes in Computer Science(), vol 8814. Springer, Cham. https://doi.org/10.1007/978-3-319-11758-4_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-11758-4_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11757-7
Online ISBN: 978-3-319-11758-4
eBook Packages: Computer ScienceComputer Science (R0)