1.College of Electrical and Information Engineering, Hunan University, Changsha 410082 2.School of Information Science and Engineering, Central South University, Changsha 410075 3.ChangSha Branch Office of China XINDA Asset Management Corporation, Changsha 410001
Abstract ART-2 based on adaptive resonance theory is a kind of self-organizing neural network and usually utilized in pattern clustering and recognition, etc. In order to satisfy some specific requirements of certain applications or to simplify the hardware implementation,some improved versions of ART-2 have been put forward in recent years. In this paper, the original ART-2 is briefly introduced, its training algorithm is firstly analyzed, and its inherent limitations are explored. The background, objects and implementation of typical improved versions are summarized and generalized, and their properties and suitabilities are remarked on. Finally, the theoretical value and some rules pointing to future application and improvement of ART-2 are shown.
[1] Carpenter G A, Grossberg S. A Massively Parallel Architecture for a Self-Organizing Neural Pattern Recognition Machine. Computer Vision, Graphics and Image Processing, 1987, 37(1): 54-115 [2] Carpenter G A, Grossberg S. ART-2: Self-Organization of Stable Category Recognition Codes for Analog Input Pattern. Applied Optics, 1987, 26(23): 4919-4930 [3] Carpenter G A, Grossberg S. ART-3: Hierarchical Search Using Chemical Transmitters in Self-Organizing Pattern Recognition Architectures. Neural Networks, 1990, 3(2): 129-152 [4] Carpenter G A, Grossberg S, Rosen D B. ART-2A: An Adaptive Resonance Algorithm for Rapid Category Learning and Recognition. Neural Networks, 1991, 4(4): 493-504 [5] Carpenter G A, Grossberg S, Rosen D B. Fuzzy ART: Fast Stable Learning and Categorization of Analog Patterns by an Adaptive Resonance System. Neural Networks, 1991, 4(6): 759-771 [6] Cao Yongqiang, Wu Jianhong. Projective ART for Clustering Data Sets in High Dimensional Spaces. Neural Networks, 2002,15(1): 105-120 [7] Cao Yongqiang, Wu Jianhong. Dynamics of Projective Adaptive Resonance Theory Model: The Foundation of PART Algorithm. IEEE Trans on Neural Networks, 2004, 15(2): 245-260 [8] Shen Anwei, Yu Bin, Guan Haiying. Research on a Classifier Using the ART-2 Neural Network. Journal of Northern Jiaotong University, 1996, 20(2): 146-151 (in Chinese) (申岸伟,俞 斌,关海鹰.ART-2 神经网络分类器的研究.北方交通大学学报, 1996, 20(2): 146-151) [9] Shen Anwei, Yu Bin. A Kind of Method of Improving Performance of Classifier Using the ART-2 Neural Network. Signal Processing, 1996, 12(1): 28-32 (in Chinese) (申岸伟,俞 斌.一种提高ART-2神经网络分类器性能的方法.信号处理, 1996, 12(1): 28-32) [10] Tang Hongwei, Sang Nong, Cao Zhiguo, et al. Research and Improvement of ART-2 Neural Network. Infrared and Laser Engineering, 2004, 33(1): 101-106 (in Chinese) (唐红卫,桑 农,曹治国,等.ART-2神经网络的研究和改进.红外与激光工程, 2004, 33(1): 101-106) [11] Xu Yongcheng, Wen Xisen, Yi Xiaoshan, et al. ART-2A of Same Phasic Data with Different Amplitudes and Its Resolution Methods. Journal of Data Acquisition & Processing, 2001, 16(4): 393-398 (in Chinese) (徐永成,温熙森,易晓山,等. ART-2A的同相位不可分问题及其解决方法. 数据采集与处理, 2001, 16(4): 393-398) [12] Xu Yongcheng, Wen Xisen, Yi Xiaoshan, et al. New ART-2A Un-Supervised Clustering Algorithm and Its Application on BIT Fault Diagnosis. Journal of Vibration Engineering, 2002, 15(2): 167-172 (in Chinese) (徐永成,温熙森,易晓山,等.新型ART-2A算法及其在BIT故障诊断中的应用.振动工程学报, 2002, 15(2): 167-172) [13] Han Xiaoyun, Liu Ruiyan. Modification of Learning Algorithms of ART-2 Network. Journal of Data Acquisition & Processing, 1996, 11(4): 241-245 (in Chinese) (韩小云,刘瑞岩.ART-2网络学习算法的改进.数据采集与处理, 1996, 11(4): 241-245) [14] Ma Jisheng. A New ART-2 Neural Network Model. Pattern Recognition and Artificial Intelligence, 2000, 13(2): 231-234 (in Chinese) (马吉胜.一种新的ART-2神经网络模型.模式识别与人工智能, 2000, 13(2): 231-234) [15] Xu Yinlin, Ning Xinbao, Huang Xiaolin. The Research on a Fractionizing and Fitting ART-2 Neural Network with Supervise. Acta Electronica Sinica, 2004, 32(10): 1754-1756 (in Chinese) (徐寅林,宁新宝,黄晓林.有教师指导细化拟合的ART-2神经网络的研究. 电子学报, 2004, 32(10): 1754-1756) [16] Jia Peng, Yin Junsong, Hu Dewen. An Improved ART-2 Model by Introducing Forgetting Mechanism. Computer Engineering and Application, 2006, 42(9): 60-62,98 (in Chinese) (贾 鹏,尹峻松,胡德文.引入遗忘机制的ART-2改进模型.计算机工程与应用, 2006, 42(9): 60-62,98) [17] Li Ming, Yan Chaohua, Liu Gaohang. ART-2 Neural Networks with More Vigorous Vigilance Test Criterion. Journal of Image and Graphics, 2001, 6(1): 81-85 (in Chinese) (黎 明,严超华,刘高航.具有更严格警戒测试准则的ART-2神经网络.中国图象图形学报, 2001, 6(1): 81-85) [18] Liu Junli, Chen Li. A New Method in IDS Based on ART-2 Neural Network. Microcomputer Development, 2005, 15(4): 119-121,128 (in Chinese) (刘军利,陈 莉.一种基于改进ART-2的入侵检测方法.微机发展, 2005, 15(4): 119-121,128) [19] Ai Jiaoyan, Zhu Xuefeng. MART-2: Modification in Structure and Algorithms. Computer Engineering and Application, 2003, 39(33): 110-113 (in Chinese) (艾矫燕,朱学锋.ART-2网络结构与算法的改进.计算机工程与应用, 2003, 39(33): 110-113) [20] Lü Xiujiang, Yao Guangshun, Zhao Yan, et al. An Improved Architecture Based on Typical ART-2 Neural Network // Proc of the 1st International Symposium on Systems and Control in Aerospace and Astronautics. Harbin, China, 2006: 1119-1121 [21] Qian Xiaodong, Wang Zhen’ou, Wang Yu. A Method of Data Clustering Based on Improved Algorithm of ART-2 // Proc of the International Conference on Machine Learning and Cybernetics. Guangzhou, China, 2005, Ⅳ: 2021-2026 [22] Davenport M P, Titus A H. Multilevel Category Structure in the ART-2 Network. IEEE Trans on Neural Networks, 2004, 5(1): 145-158 [23] Chen Ming, Ghorbani A A, Bhavsar V C. Adaptive Resonance Theory Networks Using Incremental Communication // Proc of the International Joint Conference on Neural Networks. Washington, USA, 2001, Ⅳ: 2774-2778 [24] Chen Ming, Ghorbani A A, Bhavsar V C. Incremental Communication for Adaptive Resonance Theory Networks. IEEE Trans on Neural Networks, 2005, 16(1): 132-144 [25] Tsai W Y, Tai H M, Reynolds A C. An ART2-BP Neural Network and Its Application to Reservoir Engineering // Proc of the IEEE World Congress on Neural Networks. Orlando, USA, 1994, Ⅴ: 3289-3294 [26] Fujita M, Bavarian B. An ART2-TPM Neural Network for Automatic Pattern Classification // Proc of the International Joint Conference on Neural Networks. Seattle, USA, 1991,Ⅱ: 479-484 [27]Yeh M F, Chiang S S. GreyART Network for Data Clustering. Neurocomputing, 2005, 67(2): 313-320
2007, Vol. 20 
