An Experimental Study of the Hybridization of Logistic Discriminant Analysis and Multilayer Neural Network for Image Identification
Akira Asano, Kazuhiro Hotta, Takao Hinamoto, Chie Muraki Asano, M Ohtaki, Mitsuji Muneyasu · 2005
A hybridized classification system of the logistic discriminant analysis and the three-layer neural network is proposed. This system is basically a linear discrimination and is assisted by the neural network only for the cases that are difficult to be classified by linear methods. This system presents a simple discrimination structure given by linear methods, and its computational cost is much lower than the exclusive use of the neural network while the misclassification rate is as low as the neural network. The ability of this system is shown experimentally in the case of applying it to image identification problems. The computation time for the learning process is reduced to one-fifth by this method in this experiment, while the misclassification rate remains almost the same.