Handwritten numeral recognition using autoassociative neural networks

本論文では自己想起回路によるパターン認識に関する基礎的考察と, 相互想起回路および統計的識別手法との比較・評価のための手書き数字認識実験の結果について報告する.統計的識別手法としては, 投影距離法と最近傍法を用いる.特にK-L展開を用いる投影距離法と3層の自己想起回路の関係について詳しく考察し, 3層および5層の自己想起回路が投影距離法より優れている点を明らかにする.手書き数字認識実験には, 郵政省郵政研究所が作成した計44, 862文字の数字データを用い, 自己想起回路と相互想起回路, 最近傍法, 投影距離法の認識率について比較・考察する.実験の結果, 5層の自己想起回路を用いた場合に最も高い認識率が得られた.また, 自己想起回路には, (1)クラスごとに学習するため相互想起回路に比べて局所解に陥りにくい, (2)最近傍法に比べてサンプルの補間・圧縮能力が高い, (3)投影距離法に比べて部分空間の共有による誤分類が生じにくい, (4)5層の自己想起回路は超曲面状の分布を近似できる, などの特色があることを基礎的な考察と実験結果のよって示す.This paper describes a result of fundamental study on pattern recognition using autoassociative neural nerworks, and experimental comparison on handwritten numeral recognition by conventional multi-layered neural network and statistical classification techniques. As the statistical classification techniques, the projection distance method and the nearest neighbor method are employed. The relationship between the projection distance method which is based on the K-L expansion and three layered autoassociative networks is discussed, and it is shown that the three and five layered autoassociative networks are superior to the projection distance method. In the handwritten numeral recognition experiment, a total of 44, 862 numeral samples collected by IPTP are used to evaluate and compare the recognition rates of the autoassociative networks, the mutual associative network, the nearest neighbor method, and the projection distance method. The five layered autoassociative networks achieved the highest recognition rate in the handwritten numeral recognition experiment. The result of experiment together with the fundamental study show that the autoassociative networks have such characteristics that:(1)class independent training makes the possibility of local convergence less than that of the mutual associative network, (2)the networks possess the higher ability of dimension reduction and interpolation than the nearest neighbor method, (3)they yield less misclassification due to subspace sharing than the projection method, (4)the five layered autoassociative network can fit a curved hypersurface to a distribution of patterns