Competitive Learning with Feedforward Supervisory Signal for Pre-trained Multilayered Networks
Neural and Evolutionary Computing
2015-02-17 v7 Computer Vision and Pattern Recognition
Machine Learning
Machine Learning
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 for robust leaning and revising internal representation in a multilayer neural network.
Cite
@article{arxiv.1312.5845,
title = {Competitive Learning with Feedforward Supervisory Signal for Pre-trained Multilayered Networks},
author = {Takashi Shinozaki and Yasushi Naruse},
journal= {arXiv preprint arXiv:1312.5845},
year = {2015}
}
Comments
This paper has been withdrawn by the author since the review process for the conference to which it was applied ended