The CMAC Learning Algorithms of Non-Overlapping Receptive Field with Variable Resolution

YANG Yan-li; CAO Guang-zhong

您当前的位置：

首页 >

文章列表页 >

The CMAC Learning Algorithms of Non-Overlapping Receptive Field with Variable Resolution

更新时间：2025-07-16

- The CMAC Learning Algorithms of Non-Overlapping Receptive Field with Variable Resolution
- Acta Electronica Sinica Vol. 30, Issue S1, Pages: 2153-2154(2002)
- 作者机构：
  
  1. 深圳大学计算机系,广东,深圳,518060
  2. 深圳大学工程与技术学院,广东,深圳,518060
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP271
- Published：2002
- 稿件说明：
移动端阅览
YANG Yan-li, CAO Guang-zhong. The CMAC Learning Algorithms of Non-Overlapping Receptive Field with Variable Resolution[J]. Acta Electronica Sinica, 2002, 30(S1): 2153-2154.
DOI：

YANG Yan-li, CAO Guang-zhong. The CMAC Learning Algorithms of Non-Overlapping Receptive Field with Variable Resolution[J]. Acta Electronica Sinica, 2002, 30(S1): 2153-2154. DOI：

摘要

本文根据CMAC的样本选取方法、权值修正方法、量化方法选择的不同

提出了一种适于可编程逻辑硬件实现的CMAC快速学习方法变分辨率无交叠感受域法.通过二维函数的学习仿真验证了此学习方法是快速有效的

在精度上有进一步的改进.

Abstract

Considering the initialization of the CMAC weight memory cells the selection of the training samples

and a quantization method of the input variable

the faster CMAC learning algorithms

variable resolution of non-overlapping receptive field is proposed

which can be conveniently realized in hardware Programming Logic Curcuit. The simulation results show that the algorithms have high convergence speed and improved accuracy.

关键词

Keywords

references

Views

822

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Analysis on the Learning Ability of Improved Sparse Distributed Memory Model

A Connection Model of CMAC Network

Related Author

PENG Hong-jing

CHEN Song-can

Jiang Wenbin

Related Institution

Dept.of Computer Science and Engineering,Nanjing University of Aeronautics and Astronautics

Dept. of Physics,Huaibei Coal teachers College

⁰