| 基于离散Hopfield神经网络的数字识别实现 |
| |
| 引用本文： | 金灿.基于离散Hopfield神经网络的数字识别实现[J].计算机时代,2012(3):1-3. |
| |
| 作者姓名： | 金灿 |
| |
| 作者单位： | 中南大学信息科学与工程学院,湖南长沙410083;湖南文理学院现代教育技术中心 |
| |
| 摘 要： | 介绍了离散Hopfield神经网络的基本概念；以MATLAB为工具，根据Hopfield神经网络的相关知识，设计了一个具有联想记忆功能的离散型Hopfield神经网络，并给出了设计思路、设计步骤和测试结果。实验结果表明，通过联想记忆，对于带有一定噪声的数字点阵，Hopfield网络可以正确地进行识别，且当噪声强度为0．1时的识别效果较好。
|
| 关 键 词： | 离散 Hopfield神经网络 联想记忆 数字识别 |
On numerical recognition using discrete Hopfield neural network |
| |
| Jin Can.On numerical recognition using discrete Hopfield neural network[J].Computer Era,2012(3):1-3. |
| |
| Authors: | Jin Can |
| |
| Affiliation: | Jin Can(1. School of Information Science and Engineering, Central South University, Changsha, Hunan 410083, China 2. Modern Education Technology Center, Hunan University of Arts and Science) |
| |
| Abstract: | The author introduces in this paper the basic concept of discrete Hopfield neural network （DHNN）, and then designs a discrete Hopfield neural network model with associative memory function using MATLAB according to the related knowledge of DHNN. Specifically, the author presents the idea of designing, designing procedure and the testing results. The simulation shows that DHNN can correctly recognize the numerical dot matrices with noises. When noise intensity is less than 0.1, the recognition ability is satisfactory. |
| |
| Keywords: | Discrete Hopfield neural network Associative memory Numeral recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
