A self-supervised learning system for pa
β
K Yamauchi; M Oota; N Ishii
π
Article
π
1999
π
Elsevier Science
π
English
β 1022 KB
Artificial neural networks are useful tools for pattern recognition because they realize nonlinear mapping between input and output spaces. This ability is tuned by supervised learning methods such as back-propagation. In the supervised learning methods, desired outputs of the neural network are nee