Abstract
The objective of this paper is to discuss a state-of-the-art of methodology and algorithms for integrating fuzzy sets and neural networks in a unique framework for dealing with pattern recognition problems, in particular classification procedures. Methods of pattern recognition are studied in two main streams, namely supervised and unsupervised learning. We propose our own definition of fuzzy neural integrated networks. This criterion is proposed as a unifying framework for comparison of algorithms. In the first part of the this paper, classification methods based on rule sets or numerical data are reviewed, together with specific methods for handling classification in image processing. In the second part of this paper, several fuzzy neural clustering models are reviewed and compared. These models are: i) Self-Organizing Map (SOM); ii) Fuzzy Learning Vector Quantization (FLVQ); iii) Carpenter-Grossberg- Rosen Fuzzy Adaptive Resonance Theory (CGR Fuzzy ART); iv) Growing Neural Gas (GNG); and v) Fully self-Organizing Simplified Adaptive Resonance Theory (FOSART).
The introduction and Part I of this work have been authored by A. Petrosino, whereas Part II has been authored by A. Baraldi and P. Blonda.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
J. M. Keller and D. J. Hunt. Incorporating fuzzy membership functions into the perceptron algorithm. IEEE Trans. Pattern Analysis Machine Intelligence, 7 (6), 693–699, 1985.
C.-T. Lin and C. S. G. Lee. Neural Fuzzy Systems, Prentice Hall PTR, 1996.
J.-S. R. Jang, C.-T. Sun and E. Mizutani, Neuro-fuzzy and Soft Computing, Prentice Hall PTR, 1997.
L. A. Zadeh. Fuzzy sets. Information Control, 8, 338–353, 1965.
L. A. Zadeh. Outline of a new approach to the analysis of compe systems and decision processes. IEEE Trans. System Man and Cybernetics, 1, 28–44, 1973.
M. Umano, M. Mizumoto and K. Tanaka. FTDS systems: a fuzzy set manipulation system. Information Science, 14, 115–159, 1978.
K. Uehara and M. Fujise. Fuzzy inference based on families of α–level sets. IEEE Trans. on Fuzzy Ssytems, 1 (2), 111–124, 1993.
H. Ishibuchi and H. Tanaka. Fuzzy regression analysis using neural networks. Fuzzy sets and systems, 50, 257–265, 1992.
H. Ishibuchi, R. Fujioka and H. Tanaka. Neural networks that learn from fuzzy if-then rules. IEEE Trans. on Fuzzy Systems, 1 (2), 85–97, 1993.
C.-T. Lin and Y.-C. Lu. A neural fuzzy system with fuzzy supervised learning. IEEE Trans. on System Man and Cybernetics, 26 (5), 744–763, 1996.
L. X. Wang and J. M. Mendel. Fuzzy basis functions, universal approximation and orthogonal least-squares learning. IEEE Trans, on Neural Networks, 3 (5), 807–814, 1992.
H. M. Kim and J. M. Mendel. Fuzzy basis functions: comparisons with other basis functions. IEEE Trans, on Fuzzy Systems, 3 (2), 158–168, 1995.
F. Casalino, F. Masulli and A. Sperduti. Rule specialization in networks of fuzzy basis functions. Internat. Journal of Intelligent Automation and Soft Computing, in press, 1997.
J.-S. R. Jang. ANFIS: Adaptive-network-based fuzzy inference systems. IEEE Trans, on System Man and Cybernetics, 23 (3), 665–685, 1993.
T. Takagi and M. Sugeno. Fuzzy identification of systems and its applications to modeling and control. IEEE Trans. System Man and Cybernetics, 15 (1), 116–132, 1985.
R. R. Yager. Modeling and formulating fuzzy knowledge bases using neural networks. Neural Networks, 7 (8), 1273–1283, 1994.
T. Poggio and F. Girosi. Networks for approaximation and learning. IEEE Proceedings, 78 (9), 1481–1497, 1990.
M. M. Gupta. Fuzzy logic and neural networks, Proc. of Tenth Intern. Conf. on Multicriterion Decision Making, Taipei, 281–294, 1992.
R. Krishnapuram and L. F. Lee. Fuzzy-set-based hierarchical networks for information fusion in computer vision. Neural Networks, 5, 335–350, 1992.
S. K. Pal and S. Mitra. Multilayer perceptron, fuzzy sets and classification. IEEE Trans. on Neural Networks, 3 (5), 683–697, 1992.
P. K. Simpson. Fuzzy min–max neural networks — Part I: Classification. IEEE Trans, on Neural Networks, 3 (5), 776–786, 1992.
R. O. Duda and P. E. Hart. Pattern Classification and Scene Analysis, New York, John Wiley, 1973.
W. E. Blanz and S. L. Gish. A connectionist classifier architecture applied to image segmentation. Proc. 10th Intern. Conf Pattern Recognition, 272–277, Atlantic City, NJ.
B. S. Manjunath, T. Simchony and R. Chelappa. Stochastic and deterministic networks for texture segmentation. IEEE Trans. Acoustic Speech and Signal Processing, 38 (6), 1039–1049, 1990.
A. De Luca and S. Termini. A definition of nonprobabilistic entropy in the setting of fuzzy set theory. Information Control, 20, 301–312, 1972.
A. Kandel. Fuzzy Mathematical Techniques with Applications, New-York, 1975.
A. Ghosh, N. R. Pal and S. K. Pal. Self-organization for object extraction using a multilayer neural network and fuzziness measures. IEEE Trans. on Fuzzy Systems, 1 (2), 54–68, 1993.
A. Ghosh. Use of fuzziness measures in layered networks for object extraction: a generalization. Fuzzy sets and systems, 72, 331–348, 1995.
E. R. Caianiello and A. Petrosino. Neural networks, fuzziness and image processing, in Machine and Human Perception: Analogies and Divergencies, (V. Cantoni Ed.), 355–370, Plenum Press, New York, 1994.
A. Petrosino. Rough fuzzy sets and unsupervised neural learning: appli¬cations in computer vision, in New Trends in Fuzzy Logic, (A. Bonarini et al. Ed.), 166–176, 1996.
C.-T. Lin and C. S. G. Lee. Neural-network-based fuzzy logic control and description system. IEEE Trans. on Computers, 40 (12), 1320–1336, 1991.
C.-T. Lin. A neural fuzzy control system with structure and parameter learning. Fuzzy sets and systems, 70, 183–212, 1995.
C.J. Lin and C.–T. Lin. An ART–based fuzzy adaptive learning control network. Proc. IEEE Intern. Con. Fuzzy Systems, 1, 1–6, Orlando, FL, 1994.
H. Takagi and I. Hayashi. NN-driven fuzzy reasoning. International Journal of Approximate Reasoning, 5 (3), 191–212, 1991.
D. Nauck and R. Kruse. NEFCLASS- A neuro-fuzzy approach for the classification of data, in Proc. of 1995 ACM Symposium on Applied Computing, (K. M. George et a I. Eds ), ACM Press, 1995.
S. K. Halgamuge and M. Glesner. Neural networks in designing fuzzy systems for real world applications. Fuzzy sets and systems, 65, 1–12, 1994.
W. Pedrycz. Fuzzy neural networks with reference neurons as pattern classifiers. IEEE Trans, on Neural Networks, 3 (5), 770–775.
R. Yasdi. Combining rough sets learning and neural learning method to deal with uncertain and imprecise information. Neurocomputing, 7, 61–84, 1995.
H. R. Berenji. A reinforment learning-based architecture for fuzzy logic control. International Journal of Approximate Reasoning, 6, 267–292, 1992.
A. Baraldi and F. Parmiggiani. Fuzzy clustering: critical analysis of the contextual mechanisms employed by three neural network models. SPIE Proc. on Applications of Fuzzy Logic Thecnology III(B. Bosacchi, J. Bezdek Eds.), SPIE Vol. 2761, 261–270, 1996.
Anonymous referee, IEEE Trans. on Neural Networks, 1997.
S. Mitra and S. K. Pal. Self-organizing neural network as a fuzzy classifier. IEEE Trans, on Systems, Man, and Cybernetics, 24 (3), 385–399, 1994.
T. Kohonen. The self-organizing map. Proceedings of the IEEE 78 (9), 1464–1480, 1990.
T. Kohonen. Self-organization and Associative Memory, 2nd Edition, Spriger Verlag, Berlin, 1988.
J. C. Bezdek and N. R. Pal. Two soft relative of learning vector quantization. Neural Networks, 8 (5), 729–743, 1995.
E. C. Tsao, J. C. Bezdek and N. R. Pal. Fuzzy Kohonen clustering network. Pattern Recognition, 27 (5), 757–764, 1994.
P. K. Simpson. Fuzzy Min-Max neural network-Part 2: Clustering. IEEE Trans, on Fuzzy Systems, 1 (1), 32–45, 1993.
T. M. Martinetz, S. G. Berkovich and K. J. Schulten. Neural-gas network for vector quantization and its application to time-series prediction. IEEE Trans, on Neural Networks 4 (4), 558–569, 1993.
M. Fontana, N. A., Borghese, and S. Ferrari, Image reconstruction using improved Neural-Gas. Proc. Italian Workshop on Neural Networks’95 (M. Marinaro and R. Tagliaferri Eds.), Singapore, World Scientific, 260–265, 1995.
G. Carpenter, S. Grossberg and D.B. Rosen. Fuzzy ART: fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Networks, 4, 759–771, 1991.
G. Carpenter, S. Grossberg, N. Maukuzon, J. Reynolds and D. B. Rosen. Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps. IEEE Trans, on Neural Networks, 3 (5), 698–713, 1992.
G. A. Carpenter and S. Grossberg. A massively parallel architecture for a self-organizing neural pattern recognition machine. Computer Vision, Graphics, and Image Processing, 37, 54–115, 1987.
G. A. Carpenter and S. Grossberg. ART2: Self–organization of stable category recognition codes for analog input patterns. Applied Optics, 26 (23), 4919–4930, 1987.
A. Baraldi and F. Parmiggiani. Fuzzy combination of the Kohonen and ART neural network models to detect statistical regularities in a random sequence of multi-valued input patterns. Proc. Int. Conf. on Neural Networks’97, Houston, TX, June 1997, in press.
B. Fritzke. A growing neural gas network learns topologies. Advances in Neural Information Processing Systems 7(G. Tesauro, D. S. Touretzky, and T. K. Leen Eds.), Cambridge, MA: MIT Press, 625–632, 1995.
B. Fritzke. Some competitive learning methods. Draft document, http: //www. neuroinformatik.ruhr — uni — bochum.de/ini/VDM/ research/gsn/DemoGNG, 1997.
A. Baraldi and F. Parmiggiani. A fuzzy neural network model capable of generating/removing neurons and synaptic links dynamically. Proc. of the II Italian Workshop on Fuzzy Logic (A. Petrosino, Ed.), World Scientific, Singapore, 1997, in press.
A. Baraldi and F. Parmiggiani. Novel neural network model combining radial basis function, competitive Hebbian learning rule, and fuzzy simplified adaptive resonance theory. SPIE Proc. on Applications of Fuzzy Logic Technology IV, San Diego, CA, July 1997, in press.
M. Bianchini and M. Gori. Optimal learning in artificial neural networks: a review of theoretical results. Neurocomputing, 13 (2–4), 313–346, 1996.
R. Serra and G. Zanarini. Complex systems and cognitive processes. Springer-Verlag, Berlin, 1990.
D. E. Rumelhart, G. E. Hinton and R. J. Williams, Learning internal representations by error propagation, Parallel Distributed Processing (D. E. Rumelhart and J. L. McClelland, Eds.), 1, 318–362, MIT Press, Cambridge, MA, 1986.
T. M. Martinetz and K. J. Schulten. Topology representing networks. Neural Networks, 7 (3), 507–522, 1994.
D. Parisi. La scienza cognitiva tra intelligenza artificiale e vita artificiale. Neuroscienze e Scienze dell’Artificiale: dal Neurone all’Intelligenza (E. Biondi et al., Eds.), Patron, Bologna, Italy, 321–341, 1991 (in Italian).
J.J. Hopfield. Neural networks and physical systems with emergent collective computational abilities. Proc. National Academy of Sciences, 74, 2554–2558, 1982.
T. Masters. Signal and Image Processing With Neural Networks. A C++ Sourcebook. Wiley, New York, 1994.
N. B. Karayannis and P. Pai. Fuzzy algorithms for learning vector quantization. IEEE Trans. on Neural Networks, 7 (5), 1196–1211, 1996.
N. B. Karayannis, and M. Ravuri. An integrated approach to fuzzy learning vector quantization and fuzzy c–means clustering. Intelligent Engineering Systems Through Artificial Neural Networks (C. H. Dagli et al Eds.), 5, ASME Press, New York, NY, 247–252, 1995.
N. B. Karayannis, J. C. Bezdek. An integrated approach to fuzzy learning vector quantization and fuzzy c–means clustering. IEEE Trans. on Fuzzy Systems, under review.
N. B. Karayannis. Learning vector quantization: A review. Int. Journal of Smart Engineering System Design, in press, 1997.
J. C. Bezdek, and N. R. Pal. Generalized clustering networks and Ko– honen’s self–organizing scheme. IEEE Trans, on Neural Networks, 4 (4), 549–557, 1993.
N. B. Karayannis, J. C. Bezdek, N. R. Pal, R. J. Hathaway and P. Pai. Repair to GLVQ: A new family of competitive learning schemes. IEEE Trans. on Neural Networks, 7 (5), 1062–1071, 1996.
A. Baraldi, P. Blonda, F. Parmiggiani, G. Pasquariello and G. Satalino. How is descending FLVQ sensitive to values of its weighting exponent?. IEEE Trans. on Neural Networks, submitted.
K. Raghu and J. M. Keller. A possibilistic approach to clustering. IEEE Trans, on Fuzzy Systems, 1 (2), 98–110, 1993.
ftp://ftp.sas. com/pub/neural/FAQ.
F. Y. Shih, J. Moh and F. Chang. A new ART-based neural architecture for pattern classification and image enhancement without prior knowledge. Pattern Recognition, 25 (5), 533–542, 1992.
J. Huang, M. Georgiopoulos and G. L. Heileman. Fuzzy ART properties. Neural Networks, 8 (2), 203–213, 1995.
S. Geman, E. Bienenstock and R. Dourstat. Neural networks and the bias/variance dilemma. Neural Computation, 4 (1), 1–58, 1992.
P. Blonda, G. Satalino, A. Baraldi and A. Bognani, “Neuro-fuzzy analysis of remote sensed antarctic data,” Proc. of the II Italian Workshop on Fuzzy Logic (A. Petrosino, Ed.), World Scientific, Singapore, 1997, in press.
Y. Pao. Adaptive pattern recognition and neural networks. Addison-Wesley, Reading, MA, 1989.
B. Fritzke. Growing cell structures — A self-organizing network for unsupervised and supervised learning. Neural Networks, 7 (9), 1441–1460, 1994.
S. Kim and and S. Mitra. Integrated Adaptive Fuzzy Clustering (IAFC) algorithm. Proc. of the Second IEEE International Conference on Fuzzy Systems, 2, 1264–1268, 1993.
B. Fritzke. Personal communication, 1997.
B. Fritzke. The LBG-U method for vector quantization — An improvement over LBG inspired from neural networks. Neural Processing Letters, 5 (1), 1997, in press.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1998 Springer-Verlag London Limited
About this paper
Cite this paper
Baraldi, A., Blonda, P., Petrosino, A. (1998). Fuzzy Neural Networks for Pattern Recognition. In: Marinaro, M., Tagliaferri, R. (eds) Neural Nets WIRN VIETRI-97. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-1520-5_2
Download citation
DOI: https://doi.org/10.1007/978-1-4471-1520-5_2
Publisher Name: Springer, London
Print ISBN: 978-1-4471-1522-9
Online ISBN: 978-1-4471-1520-5
eBook Packages: Springer Book Archive