Proceedings of the KIEE Conference (대한전기학회:학술대회논문집)

The Korean Institute of Electrical Engineers (대한전기학회)
권호 표지

Object Classification Based OR LVQ With Flexible Output layer

가변적 output layer틀 이용한 LVQ 기반 물체 분류

  • Kim, Hun-Ki (Department of Electrical, Information and Control Engineering, Hongik University) ;
  • Cho, Seong-Won (Department of Electrical, Information and Control Engineering, Hongik University) ;
  • Kim, Jae-Min (Department of Electrical, Information and Control Engineering, Hongik University) ;
  • Lee, Jin-Hyung (Department of Electrical, Information and Control Engineering, Hongik University) ;
  • Kim, Seok-Ho (Department of Electrical, Information and Control Engineering, Hongik University)
  • 김헌기 (홍익대학교 전기 정보 제어 공학과) ;
  • 조성원 (홍익대학교 전기 정보 제어 공학과) ;
  • 김재민 (홍익대학교 전기 정보 제어 공학과) ;
  • 이진형 (홍익대학교 전기 정보 제어 공학과) ;
  • 김석호 (홍익대학교 전기 정보 제어 공학과)
  • Published : 2007.10.26
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we present a new method for classifying object using LVQ (Learning Vector Quantization) with flexible output layer. The proposed LVQ is a supervised learning method that dynamically generates output neurons and initializes automatically the weight vectors from training patterns. If the classes of the nearest output neuron is different from the class of the training pattern, a new output neuron is created and the given training pattern is used to initialize the weight vector of the created neuron. The proposed method is significantly different from the previous competitive learning algorithms in the point that the output neurons are dynamically generated during the learning process.

Keywords