Advanced search
2 files | 3.59 MB Add to list

On the application of reservoir computing networks for noisy image recognition

Azarakhsh Jalalvand (UGent) , Kris Demuynck (UGent) , Wesley De Neve (UGent) and Jean-Pierre Martens (UGent)
(2018) NEUROCOMPUTING. 277. p.237-248
Author
Organization
Abstract
Reservoir Computing Networks (RCNs) are a special type of single layer recurrent neural networks, in which the input and the recurrent connections are randomly generated and only the output weights are trained. Besides the ability to process temporal information, the key points of RCN are easy training and robustness against noise. Recently, we introduced a simple strategy to tune the parameters of RCNs. Evaluation in the domain of noise robust speech recognition proved that this method was effective. The aim of this work is to extend that study to the field of image processing, by showing that the proposed parameter tuning procedure is equally valid in the field of image processing and conforming that RCNs are apt at temporal modeling and are robust with respect to noise. In particular, we investigate the potential of RCNs in achieving competitive performance on the well-known MNIST dataset by following the aforementioned parameter optimizing strategy. Moreover, we achieve good noise robust recognition by utilizing such a network to denoise images and supplying them to a recognizer that is solely trained on clean images. The experiments demonstrate that the proposed RCN-based handwritten digit recognizer achieves an error rate of 0.81 percent on the clean test data of the MNIST benchmark and that the proposed RCN-based denoiser can effectively reduce the error rate on the various types of noise. (c) 2017 Elsevier B.V. All rights reserved.
Keywords
Reservoir computing networks, Recurrent neural networks, Text recognition, Image classification, Image denoising

Downloads

  • (...).pdf
    • full text
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.90 MB
  • DS73 i.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 1.69 MB

Citation

Please use this url to cite or link to this publication:

MLA
Jalalvand, Azarakhsh et al. “On the Application of Reservoir Computing Networks for Noisy Image Recognition.” NEUROCOMPUTING 277 (2018): 237–248. Print.
APA
Jalalvand, A., Demuynck, K., De Neve, W., & Martens, J.-P. (2018). On the application of reservoir computing networks for noisy image recognition. NEUROCOMPUTING, 277, 237–248.
Chicago author-date
Jalalvand, Azarakhsh, Kris Demuynck, Wesley De Neve, and Jean-Pierre Martens. 2018. “On the Application of Reservoir Computing Networks for Noisy Image Recognition.” Neurocomputing 277: 237–248.
Chicago author-date (all authors)
Jalalvand, Azarakhsh, Kris Demuynck, Wesley De Neve, and Jean-Pierre Martens. 2018. “On the Application of Reservoir Computing Networks for Noisy Image Recognition.” Neurocomputing 277: 237–248.
Vancouver
1.
Jalalvand A, Demuynck K, De Neve W, Martens J-P. On the application of reservoir computing networks for noisy image recognition. NEUROCOMPUTING. 2018;277:237–48.
IEEE
[1]
A. Jalalvand, K. Demuynck, W. De Neve, and J.-P. Martens, “On the application of reservoir computing networks for noisy image recognition,” NEUROCOMPUTING, vol. 277, pp. 237–248, 2018.
@article{8545706,
  abstract     = {Reservoir Computing Networks (RCNs) are a special type of single layer recurrent neural networks, in which the input and the recurrent connections are randomly generated and only the output weights are trained. Besides the ability to process temporal information, the key points of RCN are easy training and robustness against noise. Recently, we introduced a simple strategy to tune the parameters of RCNs. Evaluation in the domain of noise robust speech recognition proved that this method was effective. The aim of this work is to extend that study to the field of image processing, by showing that the proposed parameter tuning procedure is equally valid in the field of image processing and conforming that RCNs are apt at temporal modeling and are robust with respect to noise. In particular, we investigate the potential of RCNs in achieving competitive performance on the well-known MNIST dataset by following the aforementioned parameter optimizing strategy. Moreover, we achieve good noise robust recognition by utilizing such a network to denoise images and supplying them to a recognizer that is solely trained on clean images. The experiments demonstrate that the proposed RCN-based handwritten digit recognizer achieves an error rate of 0.81 percent on the clean test data of the MNIST benchmark and that the proposed RCN-based denoiser can effectively reduce the error rate on the various types of noise. (c) 2017 Elsevier B.V. All rights reserved.},
  author       = {Jalalvand, Azarakhsh and Demuynck, Kris and De Neve, Wesley and Martens, Jean-Pierre},
  issn         = {0925-2312},
  journal      = {NEUROCOMPUTING},
  keywords     = {Reservoir computing networks,Recurrent neural networks,Text recognition,Image classification,Image denoising},
  language     = {eng},
  pages        = {237--248},
  title        = {On the application of reservoir computing networks for noisy image recognition},
  url          = {http://dx.doi.org/10.1016/j.neucom.2016.11.100},
  volume       = {277},
  year         = {2018},
}

Altmetric
View in Altmetric
Web of Science
Times cited: