Training under achievement quotient criterion

The cost function of the training algorithm plays a very important role especially in applications of neural networks (NNs) to signal processing. In this paper, a new training algorithm under the achievement quotient criterion is proposed for preserving important information such as edges and envelopes. The experiments to reduce noise from natural and medical images were performed. By comparisons with the standard backpropagation algorithm, it has been shown that the NNs trained by the proposed training have a desirable characteristic: the performance on preserving the edges and fine structures of objects is clearly superior.

[1]  Bernard Widrow,et al.  Adaptive switching circuits , 1988 .

[2]  Werner A. Stahel,et al.  Robust Statistics: The Approach Based on Influence Functions , 1987 .

[3]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[4]  Stephen Jose Hanson,et al.  Minkowski-r Back-Propagation: Learning in Connectionist Models with Non-Euclidian Error Signals , 1987, NIPS.

[5]  Bernard Widrow,et al.  Adaptive Signal Processing , 1985 .

[6]  Timothy Masters.  Signal and Image Processing with Neural Networks: A C++ Sourcebook , 1994 .

[7]  Jaakko Astola,et al.  A new class of nonlinear filters-neural filters , 1993, IEEE Trans. Signal Process..

[8]  Kenji Suzuki,et al.  Designing the optimal structure of a neural filter , 1998, Neural Networks for Signal Processing VIII. Proceedings of the 1998 IEEE Signal Processing Society Workshop (Cat. No.98TH8378).

[9]  Andrzej Cichocki,et al.  Neural networks for optimization and signal processing , 1993 .

[10]  Isao Horiba,et al.  Efficient approximation of a neural filter for quantum noise removal in X-ray images , 1999, Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468).

[11]  Kaoru Arakawa,et al.  A nonlinear digital filter using multi-layered neural networks , 1990, IEEE International Conference on Communications, Including Supercomm Technical Sessions.

[12]  Pietro Burrascano,et al.  A norm selection criterion for the generalized delta rule , 1991, IEEE Trans. Neural Networks.

[13]  Jaakko Astola,et al.  Adaptive neural filters , 1991, Neural Networks for Signal Processing Proceedings of the 1991 IEEE Workshop.

[14]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[15]  Geoffrey E. Hinton,et al.  Learning representations of back-propagation errors , 1986 .