一种基于量子细胞自动机的三维量子细胞神经网络  

Three-dimensional quantum cellular neural networks based on quantum cellular automata

作　　者：王森[1] 蔡理[1] 李芹[1] 吴刚[1] 

机构地区：[1]空军工程大学理学院,陕西西安710051

出　　处：《量子电子学报》2008年第5期540-545,共6页Chinese Journal of Quantum Electronics

基　　金：陕西省自然基金科学基础研究计划项目(2005F20);空军工程大学理学院学位论文创新基金(2007B003)

摘　　要：以量子细胞自动机为神经元,提出了一种三维的量子细胞神经网络结构;该量子细胞网络包含上下两层的量子细胞自动机阵列,并引入了A模板、B模板以及阈值的概念。以量子细胞自动机的极化率为像素值,通过选择不同的模板、阈值等参数,使得量子细胞神经网络实现了"与"、"或"、"非"操作以及边缘提取等图像处理功能,并利用MATLAB进行了仿真验证,数值仿真结果验证了其在图像处理上的有效性。与传统的细胞神经网络相比,量子细胞神经网络易于实现超大规模且具有超低功耗、超高集成度等优点。A three-dimensional quantum cellular neural network is proposed by using the quantum cellular automata as neuron cells. The new structure of the quantum cellular neural network contains two layers of quantum cellular automata array and introduces concepts of A cloning templates, B cloning templates, and thresholds. The proposed quantum cellular neural network can perform the functions of the logic AND, OR, NOT operation, and edge extraction operation by using the polarization of quantum-dot cell as pixel value and selecting different cloning templates and thresholds. The MATLAB is employed to simulate the four operations and the results demonstrate the validity of the proposed quantum cellular neural network. Moreover, compared with the traditional cellular neural networks, the quantum cellular neural network possesses the advantages of the simplified interconnection, the extremely high packing densities and the extremely low power consumption.

关 键 词：图像处理 量子细胞神经网络 细胞神经网络 量子细胞自动机 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TN911.73[自动化与计算机技术—控制科学与工程]