自适应联想记忆细胞神经网络的优化设计

doi:10.3724/SP.J.1087.2012.00411

计算机应用 ›› 2012, Vol. 32 ›› Issue (02): 411-415.DOI: 10.3724/SP.J.1087.2012.00411

自适应联想记忆细胞神经网络的优化设计

叶波,李传东

重庆大学计算机学院，重庆 400044

收稿日期:2011-08-03 修回日期:2011-09-26 发布日期:2012-02-23 出版日期:2012-02-01
通讯作者: 叶波
作者简介:叶波(1984-)，男，四川眉山人，硕士研究生，主要研究方向：细胞神经网络;
李传东(1969-)，男，山东济宁人，教授，博士生导师，主要研究方向：神经网络、混沌控制、混杂控制。
基金资助:
国家自然科学基金资助项目(60974020)

Optimal design for adaptive associative memory cellular neural networks

YE Bo,LI Chuan-dong

College of Computer Science, Chongqing University, Chongqing 400044, China

Received:2011-08-03 Revised:2011-09-26 Online:2012-02-23 Published:2012-02-01
Contact: YE Bo

摘要/Abstract

摘要： 针对训练自适应联想记忆细胞神经网络(AM-CNN)过程收敛慢，设计出的网络抗噪性能不高的特点，通过融合蚁群优化算法和粒子群算法的思想，提出以目标网络对噪声模式的输出误差为目标函数，在目标函数的一个阈值分成的两个区间内，分别采取局部搜索和全局搜索策略，训练出AM-CNN的克隆模板的设计方法。数字模拟表明，与以往的设计方法相比，该算法能在细胞神经网络4~6次的迭代过程中稳定输出期望模式，收敛速度更快，设计出的AM-CNN性能比较稳定，并对噪声鲁棒，对高斯噪声N(0,0.8)准确率达到90%左右。

关键词: 联想记忆, 细胞神经网络, 蚁群优化算法, 参数模板

Abstract: In order to speed up the convergence of self-training AM-CNN (Associative Memories Cellular Neural Network) and enhance the performance of achieved AM-CNN, an algorithm for obtaining the space-invariant cloning templates of AM-CNN was proposed, which took the output error of objective CNN as objective function and took local searching and global searching respectively in two internals separated by a given objective function threshold, coupled with the idea of ant optimization algorithm and Particle Swarm Optimization (PSO). Concluded from the numerical simulation results, the proposed algorithm outputs the objective AM-CNN and converges quickly. Meanwhile, the performance of the achieved AM-CNN is better and more stable compared with previous methods. The achieved AM-CNN is also robust to Gauss noise of N(0,0.8) with recall rate of about 90%.

Key words: associative memory, Cellular Neural Network (CNN), ant optimization algorithm, parameter template

中图分类号:

TP183

叶波李传东. 自适应联想记忆细胞神经网络的优化设计[J]. 计算机应用, 2012, 32(02): 411-415.

YE Bo LI Chuan-dong. Optimal design for adaptive associative memory cellular neural networks[J]. Journal of Computer Applications, 2012, 32(02): 411-415.

参考文献

[1]CHUA L O, YANG L. Cellular neural networks:Theory[J]. IEEE Transactions on Circuits and Systems, 1988,35(10):1257-1272. [2]CHUA L O, YANG L. Cellular neural networks:application[J]. IEEE Transactions on Circuits and Systems, 1988,35(10):1273-1290. [3]HOPFIELD J J. Neural networks and physical systems with emergent collective computational abilities [M]// Neurocomputing: Foundations of Research. Cambridge: MIT Press, 1988: 457-464. [4]BRUCOLI M, CARNIMEO L, GRASSI G. Discrete-time cellular neural networks for associative memories with learning and forgetting capabilities [J]. IEEE Transactions on Circuits System Ⅰ: Fundamental Theory and Application, 1997, 44(7):646-650. [5]LIU DERONG, MICHEL A N. Sparsely interconnected neural networks for associative memories with applications to cellular neural networks [J]. IEEE Transactions on Circuits System Ⅱ: Analog Digit Signal Processing, 1994,41(4):295-307. [6]LIU DERONG. Cloning template design of cellular neural networks for associative memories [J]. IEEE Transactions on Circuits System Ⅰ: Fundamental Theory and Application, 1997,44(7):646-650. [7]LIU DERONG, LU ZANJUN. A new synthesis approach for feedback neural networks based on the perceptron training algorithm[J]. IEEE Transactions on Neural Networks, 1997,8(6):1468-1482. [8]LU ZANJUN, LIU DERONG. A new synthesis procedure for a class of cellular neural networks with space-invariant cloning template [J]. IEEE Transactions on Circuits System Ⅱ: Analog Digital Signal Processing, 1998,45(12):1601-1605. [9]BRUCOLI M, CARNIMEO L, GRASSI G. Heteroassociative memories via cellular neural networks [J]. International Journal of Circuit Theory and Application, 1998,26(3):231-241. [10]ZENG ZHIGANG, WANG JUN. Analysis and design of associative memories based on recurrent neural networks with linear saturation activation functions and time-varying delays [J]. Neural Computation, 2007,19(8):2149-2182. [11]ZENG ZHIGANG, WANG JUN. Design and analysis of high-capacity associative memories based on a class of discrete-time recurrent neural networks [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 2008,38(6):1525-1536. [12]ZENG ZHIGANG, WANG JUN, LIAO XIAOXIN. Stability analysis of delayed cellular neural networks described using cloning templates [J]. IEEE Transactions on Circuits and Systems Ⅰ: Regular Papers，2004, 51(11):2313-2324. [13]GIROLAMO F, ANTONIO G. Adaptive particle swarm optimization for CNN associative memories design [J]. Neurocomputing,2009, 72(16/17/18):3851-3862. [14]COLORNI A, DORIGO M, MANIEZZO V. An investigation of some properties of an "Ant algorithm" [C]// PPSN 92: Proceedings of the Parallel Problem Solving from Nature Conference. Brussels: Elsevier Publishing, 1992: 509-520. [15]DORIGO M, MANIEZZO V, COLORNI A. The ant system: Optimization by a colony of cooperating agents [J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 1996, 26(1): 29-41. [16]CHEN C-Y, YE F. Particle swarm optimization algorithm and its application to clustering analysis [C]// IEEE International Conference on Networking, Sensing and Control. Piscataway: IEEE, 2004，2: 789-794.

自适应联想记忆细胞神经网络的优化设计

Optimal design for adaptive associative memory cellular neural networks

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李开荣, 刘爽, 胡倩倩, 唐亦媛. 基于转角约束的改进蚁群优化算法路径规划[J]. 计算机应用, 2021, 41(9): 2560-2568.
[2]	李蒙蒙, 秦伟, 刘艺, 刁兴春. 结合头脑风暴优化的混合蚁群优化算法[J]. 计算机应用, 2021, 41(8): 2412-2417.
[3]	樊小毛, 熊红林, 赵淦森. 带约束的清洁排班问题模型及其求解[J]. 计算机应用, 2021, 41(2): 577-582.
[4]	汪虹余, 张彧, 杨恒, 穆楠. 基于蚁群优化算法的弱光图像显著性目标检测[J]. 计算机应用, 2021, 41(10): 2970-2978.
[5]	熊勇, 张加, 余嘉俊, 张本任, 梁萱卓, 朱奇舸. 船舶三维管路智能布局优化算法[J]. 计算机应用, 2020, 40(7): 2164-2170.
[6]	许英鑫, 孙磊, 赵建成, 郭松辉. 基于蚁群优化算法的虚拟现场可编程门阵列部署策略[J]. 计算机应用, 2020, 40(3): 747-752.
[7]	王庆荣, 王瑞峰. 基于改进粒子群算法的配电网重构策略[J]. 计算机应用, 2018, 38(9): 2720-2724.
[8]	陈暄, 徐见炜, 龙丹. 基于蚁群优化蛙跳算法的云计算资源调度算法[J]. 计算机应用, 2018, 38(6): 1670-1674.
[9]	王诏远, 王宏杰, 邢焕来, 李天瑞. 基于Spark的蚁群优化算法[J]. 计算机应用, 2015, 35(10): 2777-2780.
[10]	赖智铭, 郭躬德. 基于滑动窗口和蚁群优化算法的二次路径规划算法[J]. 计算机应用, 2015, 35(1): 172-178.
[11]	郑红星, 吴岳, 涂闯, 刘进平. 单船岸桥分配与调度集成优化模型[J]. 计算机应用, 2015, 35(1): 247-251.
[12]	许建真何婷婷何丹周曈. 基于蚁群算法的树环结构应用层组播树构建算法[J]. 计算机应用, 2013, 33(12): 3449-3452.
[13]	李秀娟杨玥蒋金叶姜立明. 蚁群优化算法在物流车辆调度系统中的应用[J]. 计算机应用, 2013, 33(10): 2822-2826.
[14]	张爱华雷小亚陈晓雷陈莉莉. 基于细胞神经网络的快速手语视频分割方法[J]. 计算机应用, 2013, 33(02): 503-506.
[15]	魏多吕光宏. 基于蚁群算法的IP网络流量矩阵估计[J]. 计算机应用, 2013, 33(01): 92-94.