Horizontal and Vertical Ensemble with Deep Representation for Classification
This addresses classification performance improvement for deep learning applications, but appears incremental as it builds on existing ensemble techniques.
The paper tackles the problem of achieving good classification performance with deep neural networks using limited labeled data by proposing Horizontal Voting, Vertical Voting, and Horizontal Stacked Ensemble methods. In the ICML 2013 Black Box Challenge, these methods helped achieve rankings of 3rd/7th and 4th/5th on public/private leaderboards.
Representation learning, especially which by using deep learning, has been widely applied in classification. However, how to use limited size of labeled data to achieve good classification performance with deep neural network, and how can the learned features further improve classification remain indefinite. In this paper, we propose Horizontal Voting Vertical Voting and Horizontal Stacked Ensemble methods to improve the classification performance of deep neural networks. In the ICML 2013 Black Box Challenge, via using these methods independently, Bing Xu achieved 3rd in public leaderboard, and 7th in private leaderboard; Jingjing Xie achieved 4th in public leaderboard, and 5th in private leaderboard.