Multi-Valued Neuron（MVN） and Multi-Thresholded Neuron（MTN）,Their Combinations and Applications

Wang Shoujue

您当前的位置：

首页 >

文章列表页 >

Multi-Valued Neuron（MVN） and Multi-Thresholded Neuron（MTN）,Their Combinations and Applications

更新时间：2025-12-08

- Multi-Valued Neuron（MVN） and Multi-Thresholded Neuron（MTN）,Their Combinations and Applications
- Acta Electronica Sinica Issue 5, (1996)
- 作者机构：
  
  中国科学院半导体所
- 作者简介：
- 基金信息：
- DOI：
  CLC： TP18
- Published：1996
- 稿件说明：
移动端阅览
[1]王守觉.多值和多阈值神经元及其网络组合与应用[J].电子学报,1996(05):1-6.

Wang Shoujue. Multi-Valued Neuron（MVN） and Multi-Thresholded Neuron（MTN）,Their Combinations and Applications[J]. Acta Electronica Sinica, 1996, (5).
[1]王守觉.多值和多阈值神经元及其网络组合与应用[J].电子学报,1996(05):1-6. DOI：

Wang Shoujue. Multi-Valued Neuron（MVN） and Multi-Thresholded Neuron（MTN）,Their Combinations and Applications[J]. Acta Electronica Sinica, 1996, (5). DOI：

摘要

本文提出了输出特性具有多值和多阈值特性的神经元。这种新神经元的功能在于它用多个阈值把输入空间划分成多个超平带，并可把各个超平带按需求归类或赋以不同的输出值作为标号。以这类神经元为基础讨论了在解决奇偶校验问题和实现特定逻辑功能方面的优越性。理论上只需一个神经元就能实现任意位的奇偶校验或任意的逻辑功能，因而特别适合在模式识别和分类中应用。论文还研究了多阈值神经元的组合问题，发现二个多阈值神经元的特定组合可以发生阈值数量的倍增现象，这为复杂多阈值神经元的模拟计算与硬件实现提供了方便途径。

Abstract

ANNs for pattern recognition with multi-valued（MV） and multi-thresholded（MT） transfer function as neurons’ nonlinearities have been proposed. The function of multithresholded neurons （MTNs） lay in the fact that it partitioned the input space into several hyperplanar zones by using many thresholds in neurons’ output transfer function

it also marked these different zones with different output values as required. On the basis of these neurons

the advantage of solving parity problem and specific logic problem was investigated. It had been shown that only one neuron was needed to solve N-bit parity problem or to perform arbitrary logic function.Therefore

it was especially suitable for pattern recognition and classification. The combination of MTNs was also investigated. It was found that two MTNs may result in the multiplication of threshold number of combined net.

关键词

Keywords

references

Views

200

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on Automatic Annotation Algorithm for Character-level Oracle-Bone Images Based on Anchor Points

Support Vector Discriminant Analysis and Its Application to Facial Expression Recognition

图像分割的新理论和新方法

VLSI Realization of Neural Network

Design of a General Purpose Neuro Processor with Digital-Analog Processing and Discussion on VLSI Integration

Related Author

CAO Shuang

ZHANG Chong-sheng

TAO Yue-feng

LÜ Ling-ling

SHEN Xia-jiong

SHI Xian-jin

ZHANG You-wei

LI Jing-wen

Related Institution

School of Computer and Information Engineering, Laboratory of the Yellow River Cultural Heritage, Henan University

School of Electric Power, North China University of Water Conservancy and Hydropower

Henan Electrochemical Education Center

School of InformationWuyi UniversityJiangmenGuangdong

School of Electronics and Information EngineeringBeihang UniversityBeijing

⁰