| 基于余弦函数的神经网络硬件实现 |
| |
| 引用本文： | 袁晓红,邹阿金.基于余弦函数的神经网络硬件实现[J].吉首大学学报(自然科学版),2001,22(4):8-10. |
| |
| 作者姓名： | 袁晓红 邹阿金 |
| |
| 作者单位： | ( 1.湖南工业职业技术学院电气系,湖南 长沙 410007;2. 长沙电力学院数计系,湖南 长沙 410077) |
| |
| 基金项目： | 国家自然科学基金资助项目 (199740 0 2 ) |
| |
| 摘 要： | 研究了正交余弦基函数神经网络模型和学习算法, 给出了仿真实例, 并提出了余弦函数基神经网络模型电路实现方案.仿真结果表明,该网络学习收敛速度快,可任意逼近非线性映射等优异性能. 此外,网络结构简单,便于电路实现, 一个余弦波振荡源经倍频即可实现隐层神经元电路.
|
| 关 键 词： | 余弦函数 神经网络 电路实现 |
| 文章编号： | 1007-2985(2001)04-0008-03 |
The Design Method of the Circuit on the Cosine Basis Function Neural Networks |
| |
| YUAN Xiao-hong ,ZOU A-jin.The Design Method of the Circuit on the Cosine Basis Function Neural Networks[J].Journal of Jishou University(Natural Science Edition),2001,22(4):8-10. |
| |
| Authors: | YUAN Xiao-hong ZOU A-jin |
| |
| Institution: | ( 1. Hunan Industry Polytechnic , Changsha 410007, Hunan China; 2. Changsha University of Electr. Power, Changsha 410077,Hunan China) |
| |
| Abstract: | The model,algorithm, emulation examples and hardwired circuit based on cosine basis function neural network are studied in detail. The emulation results show that the network has an execllent performance with its fast astringercy, and it may be arbitrarily imminent to nonlinear function. In addition, its circuit is easy to be designed because of the simple structure of cosine basis function neural network. All the neural cells are constructed with a single cosine oscillator and a series of frequency multiplier. |
| |
| Keywords: | cosine basis function neural network circuit design method |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《吉首大学学报(自然科学版)》浏览原始摘要信息 |
| 点击此处可从《吉首大学学报(自然科学版)》下载免费的PDF全文 |
