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

Takashi Shinozaki, Yasushi Naruse

Decision: submitted, no decision

Abstract: 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 and enables robust and simultaneous leaning on multilayer neural network.