pre-trained multilayered network
Competitive Learning with Feedforward Supervisory Signal for Pre-trained Multilayered Networks
Shinozaki, Takashi, Naruse, Yasushi
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.