Research on the framework of morphological associative memories

被引：9
作者：
Feng N.-Q. [1 ]
Liu C.-H. [1 ]
Zhang C.-P. [1 ]
Xu J.-C. [1 ]
Wang S.-X. [1 ]
机构：
[1] College of Computer and Information Technology, Henan Normal University, Xinxiang
来源：
Jisuanji Xuebao/Chinese Journal of Computers | 2010年 / 33卷 / 01期
关键词：
Framework; Morphological associative memories; Neural networks; Norm; Operator;
D O I：
10.3724/SP.J.1016.2010.00157
中图分类号：
学科分类号：
摘要：
The morphological associative memories (MAM) are a class of extremely new artificial neural networks. Typical objects of MAM include real MAM (RMAM), complex MAM (CMAM), morphological bidirectional associative memories (MBAM), fuzzy MAM (FMAM), enhanced FMAM (EFMAM), fuzzy MBAM (FMBAM), and so on. They have many attractive advantages and features. However, they have the same morphological theoretical base in essence and it is therefore possible to unify them in a framework of MAM. At the same time, it is one of the most important and difficult researches to construct the unified framework of associative memories. The paper tries to solve the problem. Firstly, in this paper, the algebraic structure in computing of MAM is analyzed in order to establish reliable computing base of the framework. Secondly, the basic operations and the common features in the class of MAM are analyzed, and the essential attributes and methods of MAM are extracted. On this basis, the norms and operators of MAM are defined. And finally, the main theorems of MAM are refined and proved. Thus, a unified theoretical framework of MAM is established. The significance of the framework consists in: (1) The objects of MAM are unified together in mathematics and are therefore better for revealing their peculiarities and the essence of MAM; (2) It can help people find some new methods for morphological associative memories, thereby solving more problems of associative memories, pattern recognition and fuzzy reasoning.
引用
收藏
页码：157 / 166
页数：9
相关论文
共 22 条
  • [1] Sussner P., Valle M.E., Classification of fuzzy mathematical morphologies based on concepts of inclusion measure and duality, Journal of Mathematical Imaging and Vision, 32, 2, pp. 139-159, (2008)
  • [2] Valle M.E., Sussner P., A general framework for fuzzy morphological associative memories, Fuzzy Sets and Systems, 159, 7, pp. 747-768, (2008)
  • [3] Sussner P., Valle M.E., Gray-scale morphological associative memories, IEEE Transactions on Neural Networks, 17, 3, pp. 559-570, (2006)
  • [4] Sussner P., Valle M.E., Implicative fuzzy associative memories, IEEE Transactions on Fuzzy Systems, 14, 6, pp. 793-807, (2006)
  • [5] Ritter G.X., Urcid G., Lattice algebra approach to single-neuron computation, IEEE Transactions on Neural Networks, 14, 2, pp. 282-295, (2003)
  • [6] Grana M., Sussner P., Ritter G.X., Innovative applications of associative morphological memories, Mathware and Softcomputing, 10, 3, pp. 155-168, (2003)
  • [7] Davidson J.L., Ritter G.X., Theory of morphological neural networks, Proceedings of the SPIE, Digital Optical Computing II, 1215, pp. 378-388, (1990)
  • [8] Davidson J.L., Hummer F., Morphology neural networks: An introduction with applications, IEEE Circuits System Signal Processing, 12, 2, pp. 177-210, (1993)
  • [9] Davidson J.L., Srivastava R., Fuzzy image algebra neural network for template identification, Proceedings of the 2nd Annual Midwest Electrotechnology Conference, pp. 68-71, (1993)
  • [10] Gader P.D., Won Y., Khabou M.A., Image algebra network for pattern classification, Proceedings of SPIE, Image Algebra and Morphological Image Processing V, 2300, pp. 157-168, (1994)
123