神经计算中坐标变换的网络模型(CMAC)的泛化特性
Generalization of Neural Network Model (CMAC) for Coordinate Transformation in Neural Computation
-
摘要: 在神经计算中神经网络的泛化特性是一个非常重要的内容.该文简述了小脑模型 (CMAC--Cerebellar Model Areiculation Controller)的原理和学习算法,并用仿真方法讨 论了在机器人使用的坐标变换关系(输入直角坐标值,输出机器手的关节角度)下CMAC的 泛化性能:当泛化率为1:100时CMAC仍能正常工作.系统的精度虽能满足需要,但是进一 步提高却受到限制.本文还讨论了影响精度的各种因素及可能的改进方法.
-
关键词:
- 泛化性能 /
- 小脑模型(CMAC) /
- 坐标变换
Abstract: Generalization of neural network is a very important topic for coordinate transformation in neural computation. In this paper, we describe the principle of Cerebellar Model Articulation Controller (CMAC) including its learning algorithm, and discusse the generalization of CMAC through simulation of coordinate transformation (the input is position coordinate values and the output is articulation degrees of robot). The CMAC may still run well at generalization rate 1:100. Several factors affecting the accuracy are also discussed. -
点击查看大图
计量
- 文章访问数: 2208
- HTML全文浏览量: 146
- PDF下载量: 1353
- 被引次数: 0
下载:
