On the Relation of Slow Feature Analysis and Laplacian Eigenmaps

被引:40
作者
Sprekeler, Henning [1 ]
机构
[1] Ecole Polytech Fed Lausanne, Lab Computat Neurosci, CH-1015 Lausanne, Switzerland
关键词
D O I
10.1162/NECO_a_00214
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The past decade has seen a rise of interest in Laplacian eigenmaps (LEMs) for nonlinear dimensionality reduction. LEMs have been used in spectral clustering, in semisupervised learning, and for providing efficient state representations for reinforcement learning. Here, we show that LEMs are closely related to slow feature analysis (SFA), a biologically inspired, unsupervised learning algorithm originally designed for learning invariant visual representations. We show that SFA can be interpreted as a function approximation of LEMs, where the topological neighborhoods required for LEMs are implicitly defined by the temporal structure of the data. Based on this relation, we propose a generalization of SFA to arbitrary neighborhood relations and demonstrate its applicability for spectral clustering. Finally, we review previous work with the goal of providing a unifying view on SFA and LEMs.
引用
收藏
页码:3287 / 3302
页数:16
相关论文
共 22 条
  • [1] [Anonymous], 2004, ADV NEURAL
  • [2] [Anonymous], 2002, ADV NEURAL INFORM PR
  • [3] Semi-supervised learning on Riemannian manifolds
    Belkin, M
    Niyogi, P
    [J]. MACHINE LEARNING, 2004, 56 (1-3) : 209 - 239
  • [4] Laplacian eigenmaps for dimensionality reduction and data representation
    Belkin, M
    Niyogi, P
    [J]. NEURAL COMPUTATION, 2003, 15 (06) : 1373 - 1396
  • [5] Towards a theoretical foundation for Laplacian-based manifold methods
    Belkin, Mikhail
    Niyogi, Partha
    [J]. JOURNAL OF COMPUTER AND SYSTEM SCIENCES, 2008, 74 (08) : 1289 - 1308
  • [6] Slow feature analysis yields a rich repertoire of complex cell properties
    Berkes, P
    Wiskott, L
    [J]. JOURNAL OF VISION, 2005, 5 (06): : 579 - 602
  • [7] Berkes P., 2005, COGNITIVE SCI EPRINT
  • [8] The First Order Asymptotics of the Extreme Eigenvectors of Certain Hermitian Toeplitz Matrices
    Boettcher, A.
    Grudsky, S.
    Maksimenko, E. A.
    Unterberger, J.
    [J]. INTEGRAL EQUATIONS AND OPERATOR THEORY, 2009, 63 (02) : 165 - 180
  • [9] Fergus Rob, 2009, Advances in Neural Information Processing Systems, V22, P522
  • [10] Franzius M, 2008, LECT NOTES COMPUT SC, V5163, P961, DOI 10.1007/978-3-540-87536-9_98