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
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 50 条
  • [31] Solving inverse problems via auto-encoders
    Peng P.
    Jalali S.
    Yuan X.
    Jalali, Shirin (shirin.jalali@nokia-bell-labs.com), 1600, Institute of Electrical and Electronics Engineers Inc. (01): : 312 - 323
  • [32] Bankruptcy Prediction Using Stacked Auto-Encoders
    Soui, Makram
    Smiti, Salima
    Mkaouer, Mohamed Wiem
    Ejbali, Ridha
    APPLIED ARTIFICIAL INTELLIGENCE, 2020, 34 (01) : 80 - 100
  • [33] Marginalized Denoising Auto-encoders for Nonlinear Representations
    Chen, Minmin
    Weinberger, Kilian
    Sha, Fei
    Bengio, Yoshua
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 32 (CYCLE 2), 2014, 32 : 1476 - 1484
  • [34] Improved Denoising Auto-encoders for Image Denoising
    Xiang, Qian
    Pang, Xuliang
    2018 11TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, BIOMEDICAL ENGINEERING AND INFORMATICS (CISP-BMEI 2018), 2018,
  • [35] An Auditory Measure for Anomaly Detection based on Auto-encoders
    Liu, Tao
    Duan, Meiqian
    Sun, Luyang
    Zhang, Bo
    2022 ASIA CONFERENCE ON ALGORITHMS, COMPUTING AND MACHINE LEARNING (CACML 2022), 2022, : 109 - 114
  • [36] An ensemble of autonomous auto-encoders for human activity recognition
    Garcia, Kemilly Dearo
    de Sa, Claudio Rebelo
    Poel, Mannes
    Carvalho, Tiago
    Mendes-Moreira, Joao
    Cardoso, Joao M. P.
    Carvalho, Andre C. P. L. F. de
    Kok, Joost N.
    NEUROCOMPUTING, 2021, 439 : 271 - 280
  • [37] Embarrassingly shallow auto-encoders for dynamic collaborative filtering
    Olivier Jeunen
    Jan Van Balen
    Bart Goethals
    User Modeling and User-Adapted Interaction, 2022, 32 : 509 - 541
  • [38] Automatic selection of latent variables in variational auto-encoders
    Jouffroy, Emma
    Giremus, Audrey
    Berthoumieu, Yannick
    Bach, Olivier
    Hugget, Alain
    2022 30TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2022), 2022, : 1407 - 1411
  • [39] Stacked Convolutional Auto-Encoders for Steganalysis of Digital Images
    Tan, Shunquan
    Li, Bin
    2014 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2014,
  • [40] Explicit guiding auto-encoders for learning meaningful representation
    Yanan Sun
    Hua Mao
    Yongsheng Sang
    Zhang Yi
    Neural Computing and Applications, 2017, 28 : 429 - 436