From local neural networks to granular neural networks: A study in information granulation

In this study, we are concerned with a construction of granular neural networks (GNNs)-architectures formed as a direct result reconciliation of results produced by a collection of local neural networks constructed on a basis of individual data sets. Being cognizant of the diversity of the results produced by the collection of networks, we arrive at the concept of granular neural network, producing results in the form of information granules (rather than plain numeric entities) that become reflective of the diversity of the results generated by the contributing networks. The design of a granular neural network exploits the concept of justifiable granularity. Introduced is a performance index quantifying the quality of information granules generated by the granular neural network. This study is illustrated with the aid of machine learning data sets. The experimental results provide a detailed insight into the developed granular neural networks.

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

[2]  Witold Pedrycz,et al.  Logic-Based Fuzzy Neurocomputing With Unineurons , 2006, IEEE Transactions on Fuzzy Systems.

[3]  Harinder P. Singh,et al.  Fuzzy Sets and Information , 2010 .

[4]  Abdulkadir Sengür,et al.  Effective diagnosis of heart disease through neural networks ensembles , 2009, Expert Syst. Appl..

[5]  Witold Pedrycz,et al.  Granular neural networks , 2001, Neurocomputing.

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

[7]  L. Zadeh.  The role of fuzzy logic in the management of uncertainty in expert systems , 1983 .

[8]  Michael Green,et al.  Exploring new possibilities for case-based explanation of artificial neural network ensembles , 2009, Neural Networks.

[9]  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.

[10]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[11]  Witold Pedrycz,et al.  Logic-oriented neural networks for fuzzy neurocomputing , 2009, Neurocomputing.

[12]  Witold Pedrycz,et al.  A granular-oriented development of functional radial basis function neural networks , 2008, Neurocomputing.

[13]  Kazuyuki Murase,et al.  Progressive interactive training: A sequential neural network ensemble learning method , 2009, Neurocomputing.

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

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

[16]  David G. Stork,et al.  Pattern Classification , 1973 .

[17]  Vijay K. Rohatgi,et al.  Advances in Fuzzy Set Theory and Applications , 1980 .

[18]  Lotfi A. Zadeh,et al.  Fuzzy sets and information granularity , 1996 .

[19]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[20]  R. Schapire.  The Strength of Weak Learnability , 1990, Machine Learning.

[21]  Pablo M. Granitto,et al.  Neural network ensembles: evaluation of aggregation algorithms , 2005, Artif. Intell..

[22]  V. David,et al.  Searching for a solution to the automatic RBF network design problem , 2002 .

[23]  Minrui Fei,et al.  A fast multi-output RBF neural network construction method , 2010, Neurocomputing.

[24]  Sung-Bae Cho,et al.  Evolutionary ensemble of diverse artificial neural networks using speciation , 2008, Neurocomputing.