|
|||||
|
|
| 基于自适应共振理论(ART)网络的机床设备实例的分类 | |
| 引用本文： | 陈桦,程云艳,陈静,赵汝嘉.基于自适应共振理论(ART)网络的机床设备实例的分类[J].组合机床与自动化加工技术,2004(10):33-34,36. |
| 作者姓名： | 陈桦 程云艳 陈静 赵汝嘉 |
| 作者单位： | 1. 西安交通大学,研究所,陕西,西安,710049;陕西科技大学,计算机与信息工程学院,陕西,咸阳,712081 2. 陕西科技大学,计算机与信息工程学院,陕西,咸阳,712081 3. 西安交通大学,研究所,陕西,西安,710049 |
| 摘 要： | 阐述了自适应共振理论(ART)网络的原理及训练算法.利用ART网络良好的自组织,自学习,可塑性强的特点,提出基于神经网络的机床设备实例分类的策略.该方法求解简单快速,容易实现,效率高,在实际工程中具有良好的应用前景. |
| 关 键 词： | ART1网络 分类 编码 实例 |
| 文章编号： | 1001-2265(2004)10-0033-03 |
Classifying of cases model by means of ART neural network in machine equipment |
|
| CHEN Hua,CHENG Yunyan,CHEN Jing,ZHAO Rujia.Classifying of cases model by means of ART neural network in machine equipment[J].Modular Machine Tool & Automatic Manufacturing Technique,2004(10):33-34,36. | |
| Authors: | CHEN Hua CHENG Yunyan CHEN Jing ZHAO Rujia |
| Affiliation: | CHEN Hua CHENG Yunyan CHEN Jing ZHAO Rujia |
| Abstract: | This paper expatiates the principle and train algorithm of adaptive resonance theory. A new approach to the neural classifying model of machine equipment is presented on the base of its self-learning and self-orgnizing characteristics. The advantages of this model are the more effective classifying and the easier knowledge acquisition based on neural networks which has a bright application future. |
| Keywords: | ART1 network classing coding cases |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |