TY - GEN
T1 - Towards using Reservoir Computing Networks for noise-robust image recognition
AU - Jalalvand, Azarakhsh
AU - De Neve, Wesley
AU - Van De Walle, Rik
AU - Martens, Jean Pierre
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/10/31
Y1 - 2016/10/31
N2 - 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.
AB - 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.
KW - Image classification
KW - Image denoising
KW - Recurrent neural networks
KW - Reservoir computing networks
KW - Text recognition
UR - http://www.scopus.com/inward/record.url?scp=85007206563&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85007206563&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2016.7727398
DO - 10.1109/IJCNN.2016.7727398
M3 - Conference contribution
AN - SCOPUS:85007206563
T3 - Proceedings of the International Joint Conference on Neural Networks
SP - 1666
EP - 1672
BT - 2016 International Joint Conference on Neural Networks, IJCNN 2016
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2016 International Joint Conference on Neural Networks, IJCNN 2016
Y2 - 24 July 2016 through 29 July 2016
ER -