On Structure Design for RBF Neural Network Based on Information Strength

Based on the systemic investigation on the feedforword neural network, for the problem of the structure design of the RBF neural network, a new flexible structure design method is used for RBF neural network in this paper. By computing the output-information (OI) of the hidden neurons and the multi-information (MI) of the hidden nodes and output nodes, the hidden nodes in the RBF neural network can be inserted or pruned, thus the topology of the network can be modulated. This method can effectively solve the structure design of the RBF neural network. The grad-descent method for the parameter adjusting ensures the exactitude of the flexible RBF neural network (F-RBF). The structure of the RBF neural network is self-organizing, and the parameters are self-adaptive. In the end, the proposed F-RBF is used for approximating the classical non-linear functions and modelling key parameters of the wastewater treatment process. The results show that the F-RBF obtains a favorable dynamic character response and the approximating ability. Especially, comparied with the minimal resource allocation networks (MRAN), the generalized growing and pruning RBF (GGAP-RBF) and the self-organizing RBF (SORBF), the proposed algorithm is more effective in terms of training time, generalization, and neural network structure.

[1]  Vincenzo Piuri,et al.  A Hierarchical RBF Online Learning Algorithm for Real-Time 3-D Scanner , 2010, IEEE Transactions on Neural Networks.

[2]  Narasimhan Sundararajan,et al.  A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation , 2005, IEEE Transactions on Neural Networks.

[3]  Luigi Grippo,et al.  Convergent Decomposition Techniques for Training RBF Neural Networks , 2001, Neural Computation.

[4]  Scott D. Sudhoff,et al.  Self-Organizing Radial Basis Function Network for Real-Time Approximation of Continuous-Time Dynamical Systems , 2008, IEEE Transactions on Neural Networks.

[5]  J. Kotaleski,et al.  Modelling the molecular mechanisms of synaptic plasticity using systems biology approaches , 2010, Nature Reviews Neuroscience.

[6]  Marimuthu Palaniswami,et al.  Effects of moving the center's in an RBF network , 2002, IEEE Trans. Neural Networks.

[7]  Maria Bortman,et al.  A Growing and Pruning Method for Radial Basis Function Networks , 2009, IEEE Transactions on Neural Networks.

[8]  Junfei Qiao,et al.  An efficient self-organizing RBF neural network for water quality prediction , 2011, Neural Networks.

[9]  Guilherme Neves,et al.  Synaptic plasticity, memory and the hippocampus: a neural network approach to causality , 2008, Nature Reviews Neuroscience.

[10]  E Lin.  An Application of Improved RBF Neural Network in Modulation Recognition , 2007 .

[11]  Hsuan-Ming Feng,et al.  Self-generation RBFNs using evolutional PSO learning , 2006, Neurocomputing.

[12]  Xabier E. Barandiaran,et al.  On the nature of neural information: A critique of the received view 50 years later , 2008, Neurocomputing.

[13]  Y Lu,et al.  A Sequential Learning Scheme for Function Approximation Using Minimal Radial Basis Function Neural Networks , 1997, Neural Computation.

[14]  Qiao Junfei,et al.  Optimal Structure Design for RBFNN Structure , 2010 .

[15]  Héctor Pomares,et al.  Multiobjective evolutionary optimization of the size, shape, and position parameters of radial basis function networks for function approximation , 2003, IEEE Trans. Neural Networks.

[16]  Francisco Herrera,et al.  A study on the use of imputation methods for experimentation with Radial Basis Function Network classifiers handling missing attribute values: The good synergy between RBFNs and EventCovering method , 2010, Neural Networks.

[17]  Daniel W. C. Ho,et al.  A new training and pruning algorithm based on node dependence and Jacobian rank deficiency , 2006, Neurocomputing.

[18]  John C. Platt.  A Resource-Allocating Network for Function Interpolation , 1991, Neural Computation.

[19]  Jun Wu,et al.  Nonlinear system modeling and predictive control using the RBF nets-based quasi-linear ARX model☆ , 2009 .

[20]  Cheng-Jian Lin,et al.  A self-constructing fuzzy CMAC model and its applications , 2007, Inf. Sci..