Competitive Learning with Feedforward Supervisory Signal for Pre-trained Multilayered Networks

12/20/2013

∙

by   Takashi Shinozaki, et al.

∙

0

∙

share

We propose a novel learning method for multilayered neural networks which uses feedforward supervisory signal and associates classification of a new input with that of pre-trained input. The proposed method effectively uses rich input information in the earlier layer for robust leaning and revising internal representation in a multilayer neural network.