Title :
A study of a divided learning method
Author :
Yoshida, Masao ; Iwata, Akira ; Iijima, Nobukazu ; Ejiri, Ryuichi ; Izumi, Hiroyuki ; Sone, Mototaka ; Mitsui, Hideo
Abstract :
A new learning method is proposed called the divided learning method. It is able to learn a large number of data. The method is based on human learning. Selecting the number of neurons in the hidden layer makes the learning time almost equal to or shorter than that of the usual method. Using this method, learning for character recognition was carried out with NEURO TURBO, a neural network accelerator
Keywords :
character recognition; learning systems; neural nets; NEURO TURBO; character recognition; divided learning method; hidden layer; human learning; learning time; neural network accelerator; neurons;
Conference_Titel :
Neural Networks, 1990., 1990 IJCNN International Joint Conference on
Conference_Location :
San Diego, CA, USA
DOI :
10.1109/IJCNN.1990.137814
