Scoring and Classifying with Gated Auto-Encoders

被引:2
作者
Im, Daniel Jiwoong [1 ]
Taylor, Graham W. [1 ]
机构
[1] Univ Guelph, Sch Engn, Guelph, ON N1G 2W1, Canada
来源
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2015, PT I | 2015年 / 9284卷
关键词
D O I
10.1007/978-3-319-23528-8_33
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Auto-encoders are perhaps the best-known non-probabilistic methods for representation learning. They are conceptually simple and easy to train. Recent theoretical work has shed light on their ability to capture manifold structure, and drawn connections to density modeling. This has motivated researchers to seek ways of auto-encoder scoring, which has furthered their use in classification. Gated auto-encoders (GAEs) are an interesting and flexible extension of auto-encoders which can learn transformations among different images or pixel covariances within images. However, they have been much less studied, theoretically or empirically. In this work, we apply a dynamical systems view to GAEs, deriving a scoring function, and drawing connections to Restricted Boltzmann Machines. On a set of deep learning benchmarks, we also demonstrate their effectiveness for single and multi-label classification.
引用
收藏
页码:533 / 545
页数:13
相关论文
共 26 条
[1]  
[Anonymous], 2013, INT C MACHINE LEARNI
[2]  
[Anonymous], NIPS
[3]  
[Anonymous], ICML
[4]  
[Anonymous], 2011, ICML
[5]  
[Anonymous], ISMIR
[6]  
[Anonymous], ARXIV13061091
[7]  
[Anonymous], NIPS
[8]  
[Anonymous], GAUSSIAN BINARY REST
[9]  
[Anonymous], ICLR
[10]  
[Anonymous], 2007, ICML