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 |
Year | DOI | Venue |
---|---|---|
1990 | 10.1109/IJCNN.1990.137814 | IJCNN |
Keywords | Field | DocType |
character recognition,learning systems,neural nets,neuro turbo,divided learning method,hidden layer,human learning,learning time,neural network accelerator,neurons,neural network | Competitive learning,Instance-based learning,Active learning (machine learning),Computer science,Wake-sleep algorithm,Unsupervised learning,Artificial intelligence,Artificial neural network,Machine learning,Feature learning,Learning classifier system | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yoshida, M. | 1 | 69 | 14.97 |
akira iwata | 2 | 0 | 0.68 |
Nobukazu Iijima | 3 | 1 | 1.11 |
ryuichi ejiri | 4 | 0 | 0.34 |
hiroyuki izumi | 5 | 1 | 1.11 |
Mototaka Sone | 6 | 5 | 5.50 |
h mitsui | 7 | 0 | 0.34 |