Explicit guiding auto-encoders for learning meaningful representation. Issue 3 (March 2017)

• Record Type: Journal Article
• Authors: Sun, Yanan; Mao, Hua; Sang, Yongsheng; Yi, Zhang
• Is Part Of: Neural computing & applications. Volume 28:Issue 3(2017)
• Page Start: 429
• Page End: 436
• Publication Date: 2017-03
• Subjects: Auto-encoders -- Deep learning -- Representation learning -- Neural network; Neural networks (Computer science) -- Periodicals; Neural circuitry -- Periodicals; Artificial intelligence -- Periodicals; Neural Networks (Computer) -- Periodicals; Réseaux neuronaux (Informatique) -- Périodiques; Réseaux nerveux -- Périodiques; Intelligence artificielle -- Périodiques; 006.32
• DOI: 10.1007/s00521-015-2082-x
• Languages: English
• ISSNs: 0941-0643

Abstract

Abstract 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.