Proceedings of the Korean Institute of Intelligent Systems Conference (한국지능시스템학회:학술대회논문집)
- 1993.06a
- /
- Pages.1013-1016
- /
- 1993
An Input-correlated Neuron Model and Its Learning Characteristics
- Yamakawa, Takeshi (Department of Control Engineering and Science) ;
- Aonishi, Toru (Department of Biophysical Engineering Lsaka University) ;
- Uchino, Eiji (Department of Control Engineering and Science) ;
- Miki, Tsutomu (Department of Control Engineering and Science)
- Published : 1993.06.01
Abstract
This paper describes a new type of neuron model, the inputs of which are interfered with one another. It has a high mapping ability with only single unit. The learning speed is considerably improved compared with the conventional linear type neural networks. The proposed neuron model was successfully applied to the prediction problem of chaotic time series signal.
Keywords