A modified fuzzy ARTMAP architecture for the approximation of noisy mappings

Abstract A neural architecture, fuzzy ARTMAP, is considered here as an alternative to standard feedforward networks for noisy mapping tasks. It is one of a series of architectures based upon adaptive resonance theory or ART. Like other ART-based systems, fuzzy ARTMAP has advantages over feedforward networks and is especially suited to classification-type problems. Here it is used to approximate a noisy continuous mapping. Results show that properties that confer useful advantages for classification problems do not necessarily confer similar advantages for noisy mapping problems. One particular feature, match tracking, is found to cause overlearning of the data. A modified variant is proposed, without match tracking, that stores probability information in the map field. This information is subsequently used to compute output estimates. The proposed fuzzy ARTMAP variant is found to outperform fuzzy ARTMAP in a mapping task.

[1]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[2]  Stephen Grossberg,et al.  A massively parallel architecture for a self-organizing neural pattern recognition machine , 1988, Comput. Vis. Graph. Image Process..

[3]  Pierre Cardaliaguet,et al.  Approximation of a function and its derivative with a neural network , 1992, Neural Networks.

[4]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[5]  Arjen van Ooyen,et al.  Improving the convergence of the back-propagation algorithm , 1992, Neural Networks.

[6]  Osamu Fujita,et al.  Optimization of the hidden unit function in feedforward neural networks , 1992, Neural Networks.

[7]  LiMin Fu,et al.  Neural networks in computer intelligence , 1994 .

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

[9]  Ah-Hwee Tan,et al.  Rule Extraction, Fuzzy ARTMAP, and Medical Databases , 1993 .

[10]  Kurt Hornik,et al.  Some new results on neural network approximation , 1993, Neural Networks.

[11]  Stephen Grossberg,et al.  Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system , 1991, Neural Networks.

[12]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[13]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[14]  B. Moore,et al.  ART1 and pattern clustering , 1989 .

[15]  Geoffrey E. Hinton,et al.  Proceedings of the 1988 Connectionist Models Summer School , 1989 .

[16]  Yoshifusa Ito,et al.  Approximation of continuous functions on Rd by linear combinations of shifted rotations of a sigmoid function with and without scaling , 1992, Neural Networks.

[17]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

[18]  R. Lippmann,et al.  An introduction to computing with neural nets , 1987, IEEE ASSP Magazine.

[19]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[20]  Stephen Grossberg,et al.  ART 3: Hierarchical search using chemical transmitters in self-organizing pattern recognition architectures , 1990, Neural Networks.

[21]  Marzuki Khalid,et al.  BY FUZZY ARTMAP NEURAL NETWORK , 1997 .

[22]  Norio Baba,et al.  A new approach for finding the global minimum of error function of neural networks , 1989, Neural Networks.

[23]  Stephen Grossberg,et al.  ARTMAP: supervised real-time learning and classification of nonstationary data by a self-organizing neural network , 1991, [1991 Proceedings] IEEE Conference on Neural Networks for Ocean Engineering.

[24]  G. T. Ladd.  President's address before the New York Meeting of the American Psychological Association. , 1894 .

[25]  S. Grossberg.  How does a brain build a cognitive code , 1980 .