Deep Neural Network Learning Based on Class Encoder
Abstract：Feature representation is an important topic in pattern analysis. Deep Learning, as an end-to-end feature learning method, has achieved great success in computer vision and pattern classification. Auto-encoder network, as an unsupervised network, has achieved good results in character recognition and image classification. This project is based on the auto-encoder network, and incorporates the label information, which is important and related to classification, to propose a network of class encoder, including the data or feature based class encoder and its deep structure. Applying to image recognition field, we further propose class encoder regularized deep learning method, multi-modal class encoder network and multi-task class encoder method, and propose fast structure selection method for deep class encoder network with big data. By studying the characteristic of class encoder, we try to improve the discriminative ability and the generalization performance of deep neural network, enrich the deep learning algorithms and improve the accuracy of pattern classification.
Keywords: recognition algorithm; Feature representation; Image processing and pattern recognition; Recognition system; Deep learning
Contact:
LI Ziqing
E-mail: szli@nlpr.ia.ac.cn