On-line learning in changing environments with applications in supervised and unsupervised learning

被引：41
|
作者：
Murata, N
Kawanabe, M
Ziehe, A
Müller, KR
Amari, S
机构：
[1] Fraunhofer FIRST, D-12489 Berlin, Germany
[2] Waseda Univ, Sch Sci & Engn, Tokyo 169, Japan
[3] Univ Potsdam, Dept Comp Sci, D-14482 Potsdam, Germany
[4] RIKEN, Brain Sci Inst, Wako, Saitama 35101, Japan
来源：
NEURAL NETWORKS | 2002年 / 15卷 / 4-6期
关键词：
on-line learning; adaptive learning rate; ICA; blind source separation; stochastic gradient descent; supervised learning; unsupervised learning;
D O I：
10.1016/S0893-6080(02)00060-6
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
An adaptive on-line algorithm extending the learning of learning idea is proposed and theoretically motivated. Relying only on gradient flow information it can be applied to learning continuous functions or distributions, even when no explicit loss function is given and the Hessian is not available. The framework is applied for unsupervised and supervised learning. Its efficiency is demonstrated for drifting and switching non-stationary blind separation tasks of acoustic signals. Furthermore applications to classification (US postal service data set) and time-series prediction in changing environments are presented. (C) 2002 Elsevier Science Ltd. All rights reserved.
引用
收藏
页码：743 / 760
页数：18
相关论文
共 50 条
  • [21] Towards unsupervised learning and graphical representation for on-line handwriting script
    Gargouri, Mariem
    Touj, Sameh Masmoudi
    Ben Amara, Najoua Essoukri
    [J]. 2015 IEEE 12TH INTERNATIONAL MULTI-CONFERENCE ON SYSTEMS, SIGNALS & DEVICES (SSD), 2015,
  • [22] A self-organized growing network for on-line unsupervised learning
    Shen, FR
    Hasegawa, O
    [J]. 2004 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2004, : 11 - 16
  • [23] LEARNING STYLES, ACHIEVEMENT MOTIVATION AND SATISFACTION IN ON-LINE ENVIRONMENTS
    Fernandez Olaskoaga, Lorea
    [J]. JOURNAL OF LEARNING STYLES, 2008, 1 (02): : 153 - 169
  • [24] Adaptive and on-line learning in non-stationary environments
    Lughofer, Edwin
    Sayed-Mouchaweh, Moamar
    [J]. EVOLVING SYSTEMS, 2015, 6 (02) : 75 - 77
  • [25] User-centered fall detection using supervised, on-line learning and transfer learning
    Villar, Jose R.
    de la Cal, Enrique
    Fanez, Mirko
    Gonzalez, Victor M.
    Sedano, Javier
    [J]. PROGRESS IN ARTIFICIAL INTELLIGENCE, 2019, 8 (04) : 453 - 474
  • [26] User-centered fall detection using supervised, on-line learning and transfer learning
    José R. Villar
    Enrique de la Cal
    Mirko Fañez
    Víctor M. González
    Javier Sedano
    [J]. Progress in Artificial Intelligence, 2019, 8 : 453 - 474
  • [27] An incremental adaptive network for on-line supervised learning and probability estimation
    Lim, CP
    Harrison, RF
    [J]. NEURAL NETWORKS, 1997, 10 (05) : 925 - 939
  • [28] QuickLearn -: A novel supervised on-line learning algorithm for pattern recognition
    Akhbardeh, Alireza
    Varri, Alpo
    [J]. PROCEEDINGS OF THE 2006 IEEE MOUNTAIN WORKSHOP ON ADAPTIVE AND LEARNING SYSTEMS, 2006, : 207 - +
  • [29] A brainlike learning system with supervised, unsupervised, and reinforcement learning
    Sasakawa, Takafumi
    Hu, Jinglu
    Hirasawa, Kotaro
    [J]. ELECTRICAL ENGINEERING IN JAPAN, 2008, 162 (01) : 32 - 39
  • [30] Analysis of classification by supervised and unsupervised learning
    Sapkal, Shubhangi D.
    Kakarwal, Sangeeta N.
    Revankar, P. S.
    [J]. ICCIMA 2007: INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND MULTIMEDIA APPLICATIONS, VOL I, PROCEEDINGS, 2007, : 280 - 284
12345