バックプロパゲーション・ニューラルネットへの教師信号修正法の性能検証法

DOI Web Site Web Site 参考文献7件

書誌事項

タイトル別名
  • Performance Verification Method on Modification Techniques of Desired Outputs for Back-Propagation Neural Networks
  • バックプロパゲーション ニューラルネット エ ノ キョウシ シンゴウ シュウセ

この論文をさがす

抄録

We proposed ways to improve pattern recognition ability by combining several small back-propagation neural networks (BPNNs) [1]. We found that modifying the desired outputs according to the similarity of the input patterns (i.e., increasing desired outputs to similar classes) increases the BPNN outputs for similar classes, thus improving the generalization ability of the modular-net architecture. We evaluated the learning technique using two subfeatures extracted from handwritten digits [1]. This paper proposes a performance-verification method and presents experimental results applying learning techniques to the proposed verification-problems: 4-class, 10-class, and 20-class classification problems using two-dimensional Gaussian distribution data.

収録刊行物

参考文献 (7)*注記

もっと見る

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ