A multiclass neural network classifier with fuzzy teaching inputs

Abstract A multiclass neural network classifier with fuzzy teaching inputs is proposed. The classifier creates each class by aggregating a fuzzy prototype and several fuzzy exemplars in the hidden layer. Fuzzy inputs and all the nodes in the hidden layer are represented by trapezoidal fuzzy numbers. The classifier is trained by a two-pass learning algorithm. In pass one, a very fast one-epoch algorithm PECFUH (Prototype Expansion and Contraction of FUzzy Hyperbox) or FUNLVQ (FUzzy Number's Learning Vector Quantization) is used to train the prototypes. These prototypes will classify as many fuzzy input intances as possible. Afterward, exemplars that mean the exceptions, like the “holes”, in pattern space will be generated and expanded in pass two to classify those fuzzy input instances that cannot be correctly classified by the prototypes. A few-epoch FENCE (Fuzzy Exemplar Nested Creation and Expansion) training algorithm is proposed to create the exemplar nodes. Due to the training in pass one, the number of exemplar nodes is reduced and the learning speed is very fast during pass two. In addition, on-line adaptation is supplied in this model and the computational load is lightened. Also, nonlinearly separable instances and overlapping classes can be handled well. Furthermore, this classifier has good generalization ability for the training instances with don't-care information. The experimental results manifest that the training and recalling are fast. At the same time, they illustrate that required nodes are few.

[1]  R.P. Lippmann,et al.  Pattern classification using neural networks , 1989, IEEE Communications Magazine.

[2]  Sunanda Mitra,et al.  An adaptive fuzzy system for control and clustering of arbitrary data patterns , 1992, [1992 Proceedings] IEEE International Conference on Fuzzy Systems.

[3]  Hon Keung Kwan,et al.  A fuzzy neural network and its application to pattern recognition , 1994, IEEE Trans. Fuzzy Syst..

[4]  Patrick K. Simpson,et al.  Fuzzy min-max neural networks. I. Classification , 1992, IEEE Trans. Neural Networks.

[5]  Maher A. Sid-Ahmed,et al.  Fast learning and efficient memory utilization with a prototype based neural classifier , 1995, Pattern Recognit..

[6]  Yoichi Hayashi,et al.  A neural expert system using fuzzy teaching input , 1992, [1992 Proceedings] IEEE International Conference on Fuzzy Systems.

[7]  Patrick K. Simpson,et al.  Fuzzy min-max neural networks - Part 2: Clustering , 1993, IEEE Trans. Fuzzy Syst..

[8]  D. J. Newman,et al.  UCI Repository of Machine Learning Database , 1998 .

[9]  Sankar K. Pal,et al.  Multilayer perceptron, fuzzy sets, and classification , 1992, IEEE Trans. Neural Networks.

[10]  Hideo Tanaka,et al.  An architecture of neural networks for input vectors of fuzzy numbers , 1992, [1992 Proceedings] IEEE International Conference on Fuzzy Systems.

[11]  Cheng-I Kao,et al.  A neural network model based on fuzzy classification concept , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[12]  Chin-Liang Chang,et al.  Finding Prototypes For Nearest Neighbor Classifiers , 1974, IEEE Transactions on Computers.

[13]  James C. Bezdek,et al.  Fuzzy Kohonen clustering networks , 1994, Pattern Recognit..

[14]  Hahn-Ming Lee,et al.  Supervised fuzzy ART: training of a neural network for pattern classification via combining supervised and unsupervised learning , 1993, IEEE International Conference on Neural Networks.

[15]  H. C. Card,et al.  Linguistic interpretation of self-organizing maps , 1992, [1992 Proceedings] IEEE International Conference on Fuzzy Systems.

[16]  N. Karayiannis,et al.  A fuzzy algorithm for learning vector quantization , 1994, Proceedings of IEEE International Conference on Systems, Man and Cybernetics.

[17]  Bart Kosko,et al.  Neural networks and fuzzy systems: a dynamical systems approach to machine intelligence , 1991 .

[18]  Mark R. Lehto,et al.  An algorithm to compute the degree of match in fuzzy systems , 1992 .

[19]  James L. McClelland.  Explorations In Parallel Distributed Processing , 1988 .

[20]  Madan M. Gupta,et al.  On fuzzy neuron models , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[21]  Yuichiro Anzai,et al.  The SOLAR algorithm , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[22]  L. Zadeh,et al.  An Introduction to Fuzzy Logic Applications in Intelligent Systems , 1992 .

[23]  Shigeo Abe,et al.  A neural-network-based fuzzy classifier , 1995, IEEE Trans. Syst. Man Cybern..

[24]  Lotfi A. Zadeh,et al.  Fuzzy Sets , 1996, Inf. Control..

[25]  P. K. Simpson.  Fuzzy Min-Max Neural Networks-Part 1 : Classification , 1992 .

[26]  Takeshi Yamakawa,et al.  A design algorithm of membership functions for a fuzzy neuron using example-based learning , 1992, [1992 Proceedings] IEEE International Conference on Fuzzy Systems.

[27]  Hahn-Ming Lee,et al.  A neural network architecture for classification of fuzzy inputs , 1994 .

[28]  D. Dubois,et al.  Fuzzy real algebra: Some results , 1979 .

[29]  H. Zimmermann,et al.  Fuzzy Set Theory and Its Applications , 1993 .

[30]  Piero P. Bonissone,et al.  Linguistic summarization of fuzzy data , 1990, Inf. Sci..

[31]  Shouhong Wang,et al.  Fuzzy set representation of neural network classification boundaries , 1991, IEEE Trans. Syst. Man Cybern..

[32]  Teuvo Kohonen,et al.  Self-organization and associative memory: 3rd edition , 1989 .

[33]  Martin Brown,et al.  Intelligent Control - Aspects of Fuzzy Logic and Neural Nets , 1993, World Scientific Series in Robotics and Intelligent Systems.