Title

ART2神經網絡調整子系統結構的改進

Translated Titles

Improvements of ART2 Neural Network Adaptation System Patterns

Authors

呂秀江(Xiu-Jiang Lv);趙研(Yan Zhao);姚光順(Guang-Shun Yao);鄧豔明(Yan-Ming Deng)

Key Words

ART2 ; 神經網絡 ; 調整子系統 ; ART2 ; neural network ; adaptation system

PublicationName

機械與電子

Volume or Term/Year and Month of Publication

2005卷11期(2005 / 11 / 24)

Page #

62 - 64

Content Language

簡體中文

Chinese Abstract

ART2神經網絡是按照自適應諧振理論建立的一種自組織、無監督的人工神經網絡,可應用於連續的動態數據分類。但在實際應用中發現其理論存在“同相位不可分”的缺點。針對此問題提出了一種改進的ART2神經網絡模型結構及其算法,進行了仿真,給出了與常用ART2網絡所做仿真的結果比較。

English Abstract

ART2 is a self-organized and unsupervised artificial neural network constructed from adaptive resonance theory which can be used to classify continuous active data. We have found that the theory is limited of the same phase data with different amplitudes and insensitivity to gradual change data during the simulation of data classified with ART2 neural network. Therefore, we propose a new neural network model based on adaptive resonance theory. We provide the model construction and relevant algorithm as well as the comparison with ART2.

Topic Category 基礎與應用科學 > 資訊科學
工程學 > 機械工程
工程學 > 電機工程