A Generalized Unsupervised Competitive Learning Scheme

スポンサーリンク

概要

• 論文の詳細を見る

• In this article a Neural Network learning scheme is described, which is a generalization of VQ (Vector Quantization) and ART2a (a simplified version of Adaptive Resonance Theory 2). The basic differences between VQ and ART2a will be exhibited and it will be shown how these differences are covered by the generalized scheme. The generalized scheme enables a rich set of variations on VQ and ART2a. One such variation uses the expression ∥I∥^2+∥z_j∥^2 / ∥z_j∥・sin<(I,z_j), as the distance measure between input vector I and weight vector z_j. This variation tends to be more robust to noise than ART2a, as is shown by experiments we performed. These experiments use the same data-set as the ART2a experiments in Ref.(3).

• 社団法人電子情報通信学会の論文
• 1993-05-25

著者

• Peper Ferdinand

  The Kansai Advanced Research Center Communications Research Laboratory

• Noda H

  Sharp Corp. Tenri‐shi Jpn

• Noda Hideki

  the Kansai Advanced Research Center, Communications Research Laboratory

• Noda Hideki

  The Kansai Advanced Research Center Communications Research Laboratory

関連論文

• A Generalized Unsupervised Competitive Learning Scheme

スポンサーリンク