A hybrid algorithm for training adaptive ridgelet neural network

Ridgelet neural network is a new model of artificial neural network. In this paper, an adaptive ridgelet neural network with one single hidden-layer is constructed by substituting the ridgelet function for the S-type activation function. To obtain higher accuracy and learning speed, a hybrid algorithm for training the network is researched based on conventional ones— particle swarm optimization and stochastic gradient descending algorithm. In one generation of the swarm, the nonlinear parameters of the network, direction u, location b and scale a, are optimized by an improved PSO algorithm— ρ -PSO and the linear ones, the weights w, are optimized by stochastic gradient descending algorithm. Two suit of experiments show that this hybrid training algorithm is more accurate and speedy than the conventional ones and ridgelet neural network is a prospective tool and direction of artificial neural network.

[1]  Randall S. Sexton,et al.  Reliable classification using neural networks: a genetic algorithm and backpropagation comparison , 2000, Decis. Support Syst..

[2]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[3]  David A. Landgrebe,et al.  On Information Extraction Principles for Hyperspectral Data A White Paper , 1997 .

[4]  Shuyuan Yang,et al.  Identification of road signs using a new ridgelet network , 2005, 2005 IEEE International Symposium on Circuits and Systems.

[5]  Russell C. Eberhart,et al.  A new optimizer using particle swarm theory , 1995, MHS'95. Proceedings of the Sixth International Symposium on Micro Machine and Human Science.

[6]  Kaibo Zhou,et al.  A New Ridgelet Neural Network Training Algorithm Based on Improved Particle Swarm Optimization , 2007, Third International Conference on Natural Computation (ICNC 2007).

[7]  Licheng Jiao,et al.  A new directional multi-resolution ridgelet network , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..

[8]  J. Anthony Gualtieri,et al.  Support vector machines for hyperspectral remote sensing classification , 1999, Other Conferences.

[9]  Robert I. Damper,et al.  Band Selection for Hyperspectral Image Classification Using Mutual Information , 2006, IEEE Geoscience and Remote Sensing Letters.

[10]  Shuyuan Yang,et al.  A New Adaptive Ridgelet Neural Network , 2005, ISNN.