Feature selection using multiple auto-encoders
Xinyu Guo, Ali A. Minai, Long Jason Lu · 2017
Real-world data such as medical images and sensor measurements is usually high-dimensional and limited. Using such datasets directly in machine learning tasks can lead to poor generalization. Feature learning is a general approach for transforming high-dimensional data points to a representational space with lower dimensionality. Machine learning models can be trained efficiently with such representations. In this paper, a novel feature selection method based on multiple trained sparse auto-encoders (SAEs) is described. It works by selecting diverse, non-redundant features from multiple pinched SAEs with very narrow hidden layers, and then using these features in a more appropriately sized classifier without further feature tuning. The feature learning ability of the method is evaluated in a handwritten digits recognition task. Results show that this type of feature selection provides improved representations for a softmax classifier, and that using pinched SAEs produces results equal to or better than regular SAEs.