Influence of the Unit Number of Intermediate Layers and Networks on Learning Ability
Hideto Ide*, Hiroyuki Endo*, Sizuaki Takahashi**
* Aoyama Gakuin University, 6-16-1 Chitosedai, Setagaya, Tokyo 157, Japan
** Kogakuin University, 1-242 Nishi Shinjuku, Tokyo 160, Japan
Published:April 20, 1990
Learning ability of networks in the recognition of vocabulary, etc. using neural networks is notably influenced by the unit number of intermediate layers. In our current study, we have investigated the effects when the unit number of intermediate layers is changed during the course of learning when back-propagation is applied, thereby discussing eventual influence on the learning ability of networks.
Cite this article as:H. Ide, H. Endo, and S. Takahashi, “Influence of the Unit Number of Intermediate Layers and Networks on Learning Ability,” J. Robot. Mechatron., Vol.2 No.2, pp. 118-122, 1990.Data files: