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
  • [1] Fisher Auto-Encoders
    Elkhalil, Khalil
    Hasan, Ali
    Ding, Jie
    Farsiu, Sina
    Tarokh, Vahid
    24TH INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND STATISTICS (AISTATS), 2021, 130 : 352 - 360
  • [2] Ornstein Auto-Encoders
    Choi, Youngwon
    Won, Joong-Ho
    PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 2172 - 2178
  • [3] Transforming Auto-Encoders
    Hinton, Geoffrey E.
    Krizhevsky, Alex
    Wang, Sida D.
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2011, PT I, 2011, 6791 : 44 - 51
  • [4] Correlated Variational Auto-Encoders
    Tang, Da
    Liang, Dawen
    Jebara, Tony
    Ruozzi, Nicholas
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 97, 2019, 97
  • [5] Hyperspherical Variational Auto-Encoders
    Davidson, Tim R.
    Falorsi, Luca
    De Cao, Nicola
    Kipf, Thomas
    Tomczak, Jakub M.
    UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, 2018, : 856 - 865
  • [6] Directed Graph Auto-Encoders
    Kollias, Georgios
    Kalantzis, Vasileios
    Ide, Tsuyoshi
    Lozano, Aurelie
    Abe, Naoki
    THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 7211 - 7219
  • [7] Graph Attention Auto-Encoders
    Salehi, Amin
    Davulcu, Hasan
    2020 IEEE 32ND INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI), 2020, : 989 - 996
  • [8] Conservativeness of Untied Auto-Encoders
    Im, Daniel Jiwoong
    Belghazi, Mohamed Ishmael
    Memisevic, Roland
    THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2016, : 1694 - 1700
  • [9] TURBO: The Swiss Knife of Auto-Encoders
    Quetant, Guillaume
    Belousov, Yury
    Kinakh, Vitaliy
    Voloshynovskiy, Slava
    ENTROPY, 2023, 25 (10)
  • [10] Monte Carlo Variational Auto-Encoders
    Thin, Achille
    Kotelevskii, Nikita
    Durmus, Alain
    Panov, Maxim
    Moulines, Eric
    Doucet, Arnaud
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139 : 7258 - 7267