RBF Model Based on the KECDBN

For the dilemma in determining the structure and shortage of supervision in learning process of the deep learning feature extraction algorithm CDBN, this paper proposes a method to improve this situation by adopting KECA to extract features more deeply and effectively and then we take the extracted features as the input of RBF. We use foreign exchange series to conduct the em-pirical study which shows that the accuracy of the KECDBN-RBF model is obviously improved compared to single RBF.

[1]  Saleem A. Kassam,et al.  Quantization Based on the Mean-Absolute-Error Criterion , 1978, IEEE Trans. Commun..

[2]  T. Sellke,et al.  Adaptive stack filtering under the mean absolute error criterion , 1990 .

[3]  Alan F. Murray,et al.  A Continuous Restricted Boltzmann Machine with a Hardware-Amenable Learning Algorithm , 2002, ICANN.

[4]  Meng Joo Er,et al.  Face recognition with radial basis function (RBF) neural networks , 2002, IEEE Trans. Neural Networks.

[5]  Kezhi Mao,et al.  RBF neural network center selection based on Fisher ratio class separability measure , 2002, IEEE Trans. Neural Networks.

[6]  C. Willmott,et al.  Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance , 2005 .

[7]  Edward J. Coyle,et al.  Stack filters and the mean absolute error criterion , 1988, IEEE Trans. Acoust. Speech Signal Process..

[8]  Anoop M. Namboodiri,et al.  Learning Fingerprint Orientation Fields Using Continuous Restricted Boltzmann Machines , 2013, 2013 2nd IAPR Asian Conference on Pattern Recognition.

[9]  Alan F. Murray,et al.  Continuous restricted Boltzmann machine with an implementable training algorithm , 2003 .

[10]  Jaakko Astola,et al.  Optimal weighted order statistic filters under the mean absolute error criterion , 1991, [Proceedings] ICASSP 91: 1991 International Conference on Acoustics, Speech, and Signal Processing.

[11]  Yongliang Chen,et al.  Application of continuous restricted Boltzmann machine to identify multivariate geochemical anomaly , 2014 .

[12]  Alan F. Murray,et al.  Adaptive Sensor Modelling and Classification using a Continuous Restricted Boltzmann Machine (CRBM) , 2007, ESANN.

[13]  Whei-Min Lin,et al.  A Fault Classification Method by RBF Neural Network with OLS Learning Procedure , 2001 .

[14]  Xin Fan,et al.  Joint trajectory tracking and recognition based on bi-directional nonlinear learning , 2009, Image Vis. Comput..