Abstract
RePART is a variation of fuzzy ARTMAP to which a reward/punishment concept has been added. Previously, an improvement in performance of RePART had been noted compared with other ARTMAP-based models, such as fuzzy ARTMAP and ARTMAP-IC. In this paper, a wider investigation of RePART performance is described, in which RePART is analysed in relation to a multi-layer perceptron and a RAM-based network in a handwritten numeral recognition task. In the RePART network, a variable vigilance parameter is proposed in order to smooth the poor-generalisation problem of RePART. Firstly, the same vigilance is associated within every neuron – general variable vigilance. Secondly, an individual variable vigilance for each neuron – which takes into account its average and frequency of activation – is used. In a handwritten numeral recognition task using individual variable vigilance, RePART performance improved and demonstrated a performance comparable with alternative architectures such as fuzzy multi-layer perceptron and Radial RAM.
Similar content being viewed by others
References
Aleksander, I.: 1990, Ideal neurons for neural computers, in: Parallel Processing in Neural Systems and Computers, North-Holland, Amsterdam, pp. 225-228.
Alimi, A. M.: 1997, A neuro-fuzzy approach to recognize arabic handwritten characters, in: Internat. Conf. on Neural Networks, Vol. 4, pp. 1397-1400.
Asfour, Y. R., Carpenter, G. A., and Grossberg, S.: 1995, Landsat satellite image segmentation using the fuzzy ARTMAP neural network, in Proc. of the World Congress on Neural Networks (WCNN-95), Vol. 1, pp. 150-156, Technical Report CAS/CNS TR-95-004, Boston University, Boston, MA.
Austin, J. (ed.): 1998, RAM-based Neural Networks, World Scientific, Singapore.
Baraldi, A. and Blonda, P.: 1998, Fuzzy neural networks for pattern recognition, Technical Report, IMGA-CNR, Italy.
Bartfai, G.: 1995, An improved learning algorithm for the fuzzy ARTMAP Neural Network, Technical Report CS-TR-95-10, School of Mathematical and Computing Sciences, Victoria University.
Canuto, A.: 1995, Radial RAM: An alternative generalisation for RAM neurons, MSc. Thesis, Federal University of Pernambuco, Brazil.
Canuto, A. and Filho, E.: 1995, A generalization process to weightless neurons, in: Fourth Internat. IEE Conf. on Artificial Neural Networks, pp. 183-188.
Canuto, A. and Filho, E.: 1996, Improving recognition performance of the RAM node, in: World Congress on Neural Networks, pp. 399-402.
Canuto, A., Howells, G., and Fairhurst, M.: 1999a, RePART: A modified fuzzy ARTMAP for pattern recognition, B. Reusch (ed.), Lecture Notes in Computer Science, Vol. 1625 (Sixth Fuzzy Days, Dortmund, Germany), pp. 159-168.
Canuto, A., Howells, G., and Fairhurst, M.: 1999b, Fuzzy multi-layer perceptron for binary pattern recognition, in: 7th Internat. Conf. on Image Processing and Its Applications, Vol. 1, pp. 260-264.
Carpenter, G.: 1997, Distributed learning, recognition, and prediction by ART and ARTMAP neural networks, Neural Networks 10(8), 1473-1494.
Carpenter, G. and Grossberg, S.: 1987, A massive parallel architecture for a self-organizing neural pattern recognition machine, Computer Vision Graphics Image Process. 37, 54-115.
Carpenter, G. and Grossberg, S.: 1991, Pattern Recognition by Self-organizing Neural Networks, MIT Press, Cambridge, MA.
Carpenter, G., Grossberg, S., and Iizuka, K.: 1992, Comparative performance measures of fuzzy ARTMAP, learned vector quantization, and back propagation for handwritten character recognition, in: Internat. Joint Conf. on Neural Networks, Vol. 1, pp. 794-799.
Carpenter, G., Grossberg, S., Markunzo, N., Reynolds, J. H., and Rosen, D. B.: 1992, Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps, IEEE Trans. Neural Networks 3, 698-713.
Carpenter, G., Grossberg, S., and Reynolds, J. H.: 1991, ARTMAP: Supervised real-time learning and classification of nonstationary data by a self-organizing neural network, Neural Networks 4, 565-588.
Carpenter, G., Grossberg, S., and Rosen, D. B.: 1991, Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system, Neural Networks 4, 759-771.
Carpenter, G. and Markuzon, S.: 1998, ARTMAP-IC and medical diagnosis: instance counting and inconsistent cases, Neural Networks 11, 323-336.
Carpenter, G. and Ross, W.: 1995, ART-EMAP: A neural network architecture for object recognition by evidence accumulation, IEEE Trans. Neural Networks 6(4), 805-818.
Dagher, I., Georgiopoulos, M., Heilman, G., and Bebis, G.: 1998a, Fuzzy ARTVar: An improved fuzzy ARTMAP algorithm, in: Internat. Joint Conf. on Neural Networks (IJCNN-98), Vol. 3, Alaska, May 4-9, 1998, pp. 1688-1693.
Dagher, I., Georgiopoulos, M., Heilman, G., and Bebis, G.: 1998b, Ordered fuzzy ARTMAP:A fuzzy ARTMAP algorithm with a fixed order, in: Internat. Joint Conf. on Neural Networks (IJCNN-98), Vol. 3, Alaska, May 4-9, 1998, pp. 1717-1722.
Garris, M. D. and Wilkinson, R. A.: 1992, NIST: Special database 19, National Institute of Standards and Technology, Gaithersburg, MD, USA.
Granger, E., Grossberg, S., Rubin, M. A., and Streilein, W. W.: 1999, Familiarity discrimination of radar pulses, Technical Report CAS/CNS TR-98-027, Boston University, submitted for publication in: M. S. Kearns, S. A. Solla, and D. A. Cohn (eds), Advances in Neural Information Processing Systems 11, MIT Press, Cambridge, MA.
Grossberg, S.: 1976, Adaptive pattern classification and universal recording II: Feedback, expectation, olfaction and illusions, Biological Cybernetics 23, 187-202.
Grossberg, S., Rubin, M. A., and Streilein, W. W.: 1996, Buffered reset leads to improved compression in fuzzy ARTMAP classification of radar range profiles, Technical Report CAS/CNS-96-014, Boston University, Boston, MA.
Ham, F. M. and Han, S.: 1996, Classification of cardiac arrhythmia using fuzzy ARTMAP, IEEE Trans. Biomedical Engrg. 43(4), 425-429.
Haykin, S.: 1998, Neural Networks: A Comprehensive Foundation, 2nd edn, Prentice-Hall, Englewood Cliffs, NJ.
Hukk, J. J.: 1994, A database for handwritten text recognition, IEEE Trans. Pattern Anal. Mach. Intelligence 16(5), 550-554.
Jang, J.-S. R., Sun, C.-T., and Mizutani: 1997, Neuro-fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, Prentice-Hall, Englewood Cliffs, NJ.
Joseph, S.: 1998, Theories of adaptive neural growth, PhD Thesis, University of Edimburg.
Kan, W. and Aleksander, I.: 1987, A probabilistic logic neuron network for associative learning, Technical Report, Imperial College, University of London.
Kanerva, P.: 1988, Sparse Distributed Memory, MIT Press, Cambridge, MA.
Kasabov, N. and Kozma, R. (eds): 1999, Neuro-Fuzzy Techniques for Intelligent Information Systems, Studies in Fuzziness and Soft Computing, Vol. 30, Physica Verlag, Wurzburg.
Kasuba, T.: 1993, Simplified fuzzy ARTMAP, AI Expert 8(2), 18-25.
Keller, J. M. and Hunt, D. J.: 1985, Incorporating fuzzy membership functions into perceptron algorithm, IEEE Trans. Pattern Anal. Machine Intelligence 7(6), 693-699.
Lin, C.-T. and Lee, C. S. G.: 1996, Neural Fuzzy Systems: A Neuro-Fuzzy Synergism to Intelligent Systems, Prentice-Hall, Englewood Cliffs, NJ.
Mehrotra, K., Mohan, C. K., and Ranka, S.: 1997, Elements of Artificial Neural Networks, MIT Press, Cambridge, MA.
Meneganti, M., Saviello, F., and Tagliaferri, R.: 1998, Fuzzy neural networks for classification and detection of anomalies, IEEE Trans. Neural Networks 9(2), 848-861.
Murshed, N., Amin, A., and Singh, S.: 1998, Off-line handwritten Chinese character recognition based on structural features and fuzzy ARTMAP, in: Proc. of the Internat. Conf. on Advances in Pattern Recognition (ICAPR'98), Plymouth, UK, Springer, Berlin, pp. 334-343.
Murshed, N. A., Bortolozzi, F., and Sabourin, R.: 1996, A fuzzy ARTMAP-based classification system for detecting cancerous cells, based on the one-class problem approach, in: IEEE Proc. of Internat. Conf. on Pattern Recognition, pp. 478-482.
Nguyen, H. T. and Walker, E. A.: 1999, A First Course in Fuzzy Logic, 2nd edn, Chapman & Hall/CRC.
Pal, S. K. and Mitra, S.: 1992, Multilayer perceptron, fuzzy sets and classification, IEEE Trans. Neural Networks 3(5), 683-697.
Robins, A. and Frean, M.: 1998, Local learning algorithms for sequential learning task in neural networks, J. Adv. Comput. Intelligence 2(6).
Rumelhart, D. D., Hinton, G. E., and Williams, R. J.: 1986, Learning representations by backpropagating errors, Nature 323, 533-536.
Srinivasa, N.: 1997, Learning and generalization of noisy mappings using a modified PROBART neural network, IEEE Trans. Signal Process. 45(10), 2533-2550.
Tan, A.-H.: 1997, Cascade ARTMAP: Integrating neural computing and symbolic knowledge processing, IEEE Trans. Neural Networks 8(2), 237-250.
Tontini, G. and De Queiroz, A. A.: 1996, RBF fuzzy-ARTMAP: A new fuzzy neural network for robust on-line learning and identification of patterns, in: Proc. of the IEEE Internat. Conf. on Systems, Man, and Cybernetics, Vol. 2, pp. 1364-1369.
Torresen, J.: 1997, The convergence of back-propagation trained neural networks for values weight update frequencies, Internat. J. Neural Systems 8(3), 263-277.
Williamson, J. R.: 1996, Gaussian ARTMAP: A neural network for fast incremental learning of noisy multidimensional maps, Neural Networks 9, 881-897.
Zadeh, L. A.: 1965, Fuzzy sets, Information and Control, Vol. 8, 338-353.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Canuto, A., Howells, G. & Fairhurst, M. An Investigation of the Effects of Variable Vigilance within the RePART Neuro-Fuzzy Network. Journal of Intelligent and Robotic Systems 29, 317–334 (2000). https://doi.org/10.1023/A:1008159908688
Issue Date:
DOI: https://doi.org/10.1023/A:1008159908688