The Hebbian-LMS Learning Algorithm

被引:15
|
作者
Widrow, Bernard [1 ]
Kim, Youngsik [1 ]
Park, Dookun [1 ]
机构
[1] Stanford Univ, Dept Elect Engn, Stanford, CA 94305 USA
关键词
EQUALIZATION;
D O I
10.1109/MCI.2015.2471216
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Hebbian learning is widely accepted in the fields of psychology, neurology, and neurobiology. It is one of the fundamental premises of neuroscience. The LMS (least mean square) algorithm of Widrow and Hoff is the world's most widely used adaptive algorithm, fundamental in the fields of signal processing, control systems, pattern recognition, and artificial neural networks. These are very different learning paradigms. Hebbian learning is unsupervised. LMS learning is supervised. However, a form of LMS can be constructed to perform unsupervised learning and, as such, LMS can be used in a natural way to implement Hebbian learning. Combining the two paradigms creates a new unsupervised learning algorithm that has practical engineering applications and provides insight into learning in living neural networks. A fundamental question is, how does learning take place in living neural networks? "Nature's little secret," the learning algorithm practiced by nature at the neuron and synapse level, may well be the Hebbian-LMS algorithm.
引用
收藏
页码:37 / 53
页数:17
相关论文
共 50 条
  • [21] Introduction of an Hebbian unsupervised learning algorithm to boost the encoding capacity of Hopfield networks
    Molter, C
    Salihoglu, U
    Bersini, H
    Proceedings of the International Joint Conference on Neural Networks (IJCNN), Vols 1-5, 2005, : 1552 - 1557
  • [22] Mathematical formulations of Hebbian learning
    Wulfram Gerstner
    Werner M. Kistler
    Biological Cybernetics, 2002, 87 : 404 - 415
  • [23] Hebbian and anti-Hebbian learning for independent component analysis
    Meyer-Bäse, A
    Chen, YM
    McCullough, S
    IJCNN'01: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2001, : 920 - 925
  • [24] Bottom-up learning of explicit knowledge using a Bayesian algorithm and a new Hebbian learning rule
    Helie, Sebastien
    Proulx, Robert
    Lefebvre, Bernard
    NEURAL NETWORKS, 2011, 24 (03) : 219 - 232
  • [25] Hebbian learning and spiking neurons
    Kempter, R
    Gerstner, W
    von Hemmen, JL
    PHYSICAL REVIEW E, 1999, 59 (04): : 4498 - 4514
  • [26] Associative learning: Hebbian flies
    Glanzman, DL
    CURRENT BIOLOGY, 2005, 15 (11) : R416 - R419
  • [27] Frequency sensitive Hebbian learning
    Qiu, GP
    Booth, AW
    ICNN - 1996 IEEE INTERNATIONAL CONFERENCE ON NEURAL NETWORKS, VOLS. 1-4, 1996, : 143 - 148
  • [28] Hebbian learning and spiking neurons
    Kempter, Richard
    Gerstner, Wulfram
    van Hemmen, J. Leo
    Physical Review E. Statistical Physics, Plasmas, Fluids, and Related Interdisciplinary Topics, 1999, 59 (04):
  • [29] Mathematical formulations of Hebbian learning
    Gerstner, W
    Kistler, WM
    BIOLOGICAL CYBERNETICS, 2002, 87 (5-6) : 404 - 415
  • [30] Hebbian learning for olfactory sequences
    Johnson, Andrew J.
    Cauchi, Laura
    Miles, Christopher
    QUARTERLY JOURNAL OF EXPERIMENTAL PSYCHOLOGY, 2013, 66 (06): : 1082 - 1089