경쟁학습 신경망의 환경 적응성

Circumstance Adaptability of Competitive Learning Neural Networks

  • Choi, Doo-Il (Department of Electrical Engineering Kongju National University) ;
  • Park, Yang-Su (Department of Electrical Engineering Kongju National University)
  • 발행 : 1997.11.29

초록

When input circumstance is changed abrubtly, many nodes of Competitive Learning Neural Networks far from new input vector may never win, and therefore never learn. Various techniques to prevent these phenomena have been reported. We proposed a new technique based on Self Creating and Organizing Neural Networks, and which is compared to Self Organizing Feature Map and Frequency Sensitive Neural Networks.

키워드