Towards using Reservoir Computing Networks for noise-robust image recognition

Azarakhsh Jalalvand, Wesley De Neve, Rik Van De Walle, Jean Pierre Martens

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Scopus citations

Abstract

Reservoir Computing Network (RCN) is a special type of the 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 RCN resulted in an effective and noise-robust RCN-based model for speech recognition. The aim of this work is to extend that study to the field of image processing. In particular, we investigate the potential of RCNs in achieving a 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 conducted 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.

Original languageEnglish (US)
Title of host publication2016 International Joint Conference on Neural Networks, IJCNN 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1666-1672
Number of pages7
ISBN (Electronic)9781509006199
DOIs
StatePublished - Oct 31 2016
Externally publishedYes
Event2016 International Joint Conference on Neural Networks, IJCNN 2016 - Vancouver, Canada
Duration: Jul 24 2016Jul 29 2016

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2016-October

Conference

Conference2016 International Joint Conference on Neural Networks, IJCNN 2016
Country/TerritoryCanada
CityVancouver
Period7/24/167/29/16

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence

Keywords

  • Image classification
  • Image denoising
  • Recurrent neural networks
  • Reservoir computing networks
  • Text recognition

Fingerprint

Dive into the research topics of 'Towards using Reservoir Computing Networks for noise-robust image recognition'. Together they form a unique fingerprint.

Cite this