Granular Neural Networks: Concepts and Development Schemes

In this paper, we introduce a concept of a granular neural network and develop its comprehensive design process. The proposed granular network is formed on the basis of a given (numeric) neural network whose structure is augmented by the formation of granular connections (being realized as intervals) spanned over the numeric ones. Owing to its simplicity of the underlying processing, the interval connections become an appealing alternative of information granules to clarify the main idea. We introduce a concept of information granularity and its quantification (viewed as a level of information granularity). Being treated as an essential design asset, the assumed level of information granularity is distributed (allocated) among the connections of the network in several different ways so that certain performance index becomes maximized. Due to the high dimensionality nature of some protocols of allocation of information granularity and the nature of the allocation process itself, single-objective versions of particle swarm optimization is considered a suitable optimization vehicle. As we are concerned with the granular output of the network, which has to be evaluated with regard to the numeric target of data, two criteria are considered; namely, coverage of numeric data and specificity of information granules (intervals). A series of numeric studies completed for synthetic data and data coming from the machine learning and StatLib repositories provide a useful insight into the effectiveness of the proposed algorithm.

[1]  Lothar Thiele,et al.  Comparison of Multiobjective Evolutionary Algorithms: Empirical Results , 2000, Evolutionary Computation.

[2]  Yang-Yin Lin,et al.  A Recurrent Self-Evolving Interval Type-2 Fuzzy Neural Network for Dynamic System Processing , 2009, IEEE Transactions on Fuzzy Systems.

[3]  Paulo Cortez,et al.  Evolutionary Design of Neural Networks for Classification and Regression , 2005 .

[4]  H. Ishibuchi,et al.  A learning algorithm of fuzzy neural networks with triangular fuzzy weights , 1995 .

[5]  Hisao Ishibuchi,et al.  Improving the generalization ability of neural networks by interval arithmetic , 1998, 1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111).

[6]  J. A. Mulder,et al.  Neural Network Output Optimization Using Interval Analysis , 2009, IEEE Transactions on Neural Networks.

[7]  C. P. Wang,et al.  An intelligent sales forecasting system through integration of artificial neural networks and fuzzy neural networks with fuzzy weight elimination , 2002, Neural Networks.

[8]  Lei Huang,et al.  Robust interval regression analysis using neural networks , 1998, Fuzzy Sets Syst..

[9]  Ehsanollah Kabir,et al.  A PSO-based weighting method for linear combination of neural networks , 2010, Comput. Electr. Eng..

[10]  Hongjie Jia,et al.  Granular neural networks , 2014, Artificial Intelligence Review.

[11]  H. Ishibuchi,et al.  An architecture of neural networks with interval weights and its application to fuzzy regression analysis , 1993 .

[12]  Chin-Teng Lin,et al.  A recurrent self-organizing neural fuzzy inference network , 1999, IEEE Trans. Neural Networks.

[13]  Sung-Kwun Oh,et al.  Granular Neural Networks and Their Development Through Context-Based Clustering and Adjustable Dimensionality of Receptive Fields , 2009, IEEE Transactions on Neural Networks.

[14]  Abraham Kandel,et al.  Granular neural networks for numerical-linguistic data fusion and knowledge discovery , 2000, IEEE Trans. Neural Networks Learn. Syst..

[15]  Chia-Feng Juang,et al.  An Interval Type-2 Fuzzy-Neural Network With Support-Vector Regression for Noisy Regression Problems , 2010, IEEE Transactions on Fuzzy Systems.

[16]  Hongxing Li,et al.  Efficient learning algorithms for three-layer regular feedforward fuzzy neural networks , 2004, IEEE Trans. Neural Networks.

[17]  David McLean,et al.  On Global–Local Artificial Neural Networks for Function Approximation , 2006, IEEE Transactions on Neural Networks.

[18]  Giovanni Bortolan.  An architecture of fuzzy neural networks for linguistic processing , 1998, Fuzzy Sets Syst..

[19]  Witold Pedrycz,et al.  Knowledge transfer in system modeling and its realization through an optimal allocation of information granularity , 2012, Appl. Soft Comput..

[20]  H. Ishibuchi.  DEVELOPMENT OF FUZZY NEURAL NETWORKS , 1996 .

[21]  Z. A. Garczarczyk.  Interval neural networks , 2000, 2000 IEEE International Symposium on Circuits and Systems. Emerging Technologies for the 21st Century. Proceedings (IEEE Cat No.00CH36353).

[22]  Witold Pedrycz.  Fuzzy Modelling: Paradigms and Practice , 2011 .

[23]  Chi-Hsu Wang,et al.  Dynamical optimal training for interval type-2 fuzzy neural network (T2FNN) , 2003, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[24]  Peter J. Fleming,et al.  Multiobjective optimization and multiple constraint handling with evolutionary algorithms. I. A unified formulation , 1998, IEEE Trans. Syst. Man Cybern. Part A.

[25]  Oscar Castillo,et al.  Face Recognition With an Improved Interval Type-2 Fuzzy Logic Sugeno Integral and Modular Neural Networks , 2011, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[26]  George Panoutsos,et al.  A neural-fuzzy modelling framework based on granular computing: Concepts and applications , 2010, Fuzzy Sets Syst..

[27]  Yanqing Zhang,et al.  Granular Neural Networks With Evolutionary Interval Learning , 2008, IEEE Transactions on Fuzzy Systems.

[28]  Fang Liu,et al.  Short-Term Load Forecasting using Interval Arithmetic Backpropagation Neural Network , 2006, 2006 International Conference on Machine Learning and Cybernetics.

[29]  T.,et al.  Training Feedforward Networks with the Marquardt Algorithm , 2004 .

[30]  J. Buckley,et al.  Fuzzy neural networks: a survey , 1994 .