Explicit guiding auto-encoders for learning meaningful representation
详细信息 查看全文
- 作者：Yanan Sun ; Hua Mao ; Yongsheng Sang ; Zhang Yi
- 关键词：Auto ; encoders ; Deep learning ; Representation learning ; Neural network
- 刊名：Neural Computing and Applications
- 出版年：2017
- 出版时间：March 2017
- 年：2017
- 卷：28
- 期：3
- 页码：429-436
- 全文大小：
- 刊物类别：Computer Science
- 刊物主题：Artificial Intelligence (incl. Robotics); Data Mining and Knowledge Discovery; Probability and Statistics in Computer Science; Computational Science and Engineering; Image Processing and Computer Visi
- 出版者：Springer London
- ISSN：1433-3058
- 卷排序：28
文摘
The auto-encoder model plays a crucial role in the success of deep learning. During the pre-training phase, auto-encoders learn a representation that helps improve the performance of the entire neural network during the fine-tuning phase of deep learning. However, the learned representation is not always meaningful and the network does not necessarily achieve higher performance with such representation because auto-encoders are trained in an unsupervised manner without knowing the specific task targeted in the fine-tuning phase. In this paper, we propose a novel approach to train auto-encoders by adding an explicit guiding term to the traditional reconstruction cost function that encourages the auto-encoder to learn meaningful features. Particularly, the guiding term is the classification error with respect to the representation learned by the auto-encoder, and a meaningful representation means that a network using the representation as input has a low classification error in a classification task. In our experiments, we show that the additional explicit guiding term helps the auto-encoder understand the prospective target in advance. During learning, it can drive the learning toward a minimum with better generalization with respect to the particular supervised task on the dataset. Over a range of image classification benchmarks, we achieve equal or superior results to baseline auto-encoders with the same configuration.