| 多层自适应模式识别系统模型 |
| |
| 引用本文： | 杨国庆,陈松灿,吕军.多层自适应模式识别系统模型[J].航空学报,1993,14(2):26-32. |
| |
| 作者姓名： | 杨国庆 陈松灿 吕军 |
| |
| 作者单位： | 南京航空学院计算机系，南京航空学院计算机系，南京航空学院计算机系 南京 210016，南京 210016，南京 210016 |
| |
| 摘 要： | 在英国WISARD单层模式识别系统的基础上,借助P.Kanerva的稀疏分布存贮(SDM)的概念,提出了~种新的多层自适应模式识别系统模型(MAPR)。并就其工作过程和主要特点作了较详细的叙述,还列出了多体印刷体汉字识别的初步试验结果。MAPR用稀疏RAN阵列代替WISARD的常规RAM阵列,用对n元模式计频的训练策略代替了原系统的直接置位策略。使系统除了保持原系统的重要优点外,在大维数或非确定性模式数据识别方面,其性能有了明显改善。
|
| 关 键 词： | 模式识别 稀疏分布存贮 并行分布处理 神经元网络 |
A MULTI-LAYER ADAPTIVE PATLERN RECOGNITION SYSTEM MODEL |
| |
| Yang Guo-qing,Chen Song-can,Lu Jun.A MULTI-LAYER ADAPTIVE PATLERN RECOGNITION SYSTEM MODEL[J].Acta Aeronautica et Astronautica Sinica,1993,14(2):26-32. |
| |
| Authors: | Yang Guo-qing Chen Song-can Lu Jun |
| |
| Institution: | Depatment of Computer Nanjing Aeronautical Jnsfitute,Nanjing,210016 |
| |
| Abstract: | Based-on a single-layer pattern recognition system (WISARD) and referred to the concept of a sparse distributed memory (SDM) by P.Kanerva, this paper presents a novel multi-layer adaptive pattern recognition system model and describes in detail its processing procedures and main features. The results of primitive multi-font printed Chinese character recognition experiment are given.Unlike WISARD, MAPR replaces the normal RAM array with sparse RAM array, and the directly setting bit strategy with counting frequency training for n-tuple pattern, so that not only MAPR maintains the main advantages of WISARD, but its performance is obviously improved as well in the aspect of recognizing large-dimensional or non-deterministic pattern data. |
| |
| Keywords: | pattern recognition system sparse distrobuted memory |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《航空学报》浏览原始摘要信息 |
| 点击此处可从《航空学报》下载免费的PDF全文 |
|
