Handwritten numeral recognition using autoassociative neural networks
F Kimura, S Inoue, T Wakabayashi… - … Recognition (Cat. No …, 1998 - ieeexplore.ieee.org
Describes the result of a fundamental study on pattern recognition using autoassociative
neural networks, 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 KL expansion and three layered autoassociative networks is discussed, and it …
neural networks, 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 KL expansion and three layered autoassociative networks is discussed, and it …
Handwritten numeral recognition using autoassociative neural networks
S Inoue, S Tsuruoka, T Wakabayashi… - … Conference on Pattern …, 2002 - cir.nii.ac.jp
Describes the result of a fundamental study on pattern recognition using autoassociative
neural networks, 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 KL expansion and three layered autoassociative networks is discussed, and it …
neural networks, 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 KL expansion and three layered autoassociative networks is discussed, and it …
Showing the best results for this search. See all results