Strategies to associate memories by unsupervised learning in neural networks

被引：0
|
作者：
Agnes, E. J. [1 ]
Mizusaki, B. E. P. [1 ]
Erichsen, R., Jr. [1 ]
Brunnet, L. G. [1 ]
机构：
[1] Univ Fed Rio Grande do Sul, Inst Fis, BR-90046900 Porto Alegre, RS, Brazil
来源：
PHYSICS, COMPUTATION, AND THE MIND - ADVANCES AND CHALLENGES AT INTERFACES | 2013年 / 1510卷
关键词：
unsupervised learning; spiking neurons; homeostasis; STDP; MODEL;
D O I：
10.1063/1.4776533
中图分类号：
TP39 [计算机的应用];
学科分类号：
081203 ; 0835 ;
摘要：
In this work we study the effects of three different strategies to associate memories in a neural network composed by both excitatory and inhibitory spiking neurons, which are randomly connected through recurrent excitatory and inhibitory synapses. The system is intended to store a number of memories, associated to spatial external inputs. The strategies consist in the presentation of the input patterns through trials in: i) ordered sequence; ii) random sequence; iii) clustered sequences. In addition, an order parameter indicating the correlation between the trials' activities is introduced to compute associative memory capacities and the quality of memory retrieval.
引用
收藏
页码：255 / 257
页数：3
相关论文
共 50 条
  • [1] Unsupervised Hebbian learning in neural networks
    Freisleben, B
    Hagen, C
    [J]. COMPUTING ANTICIPATORY SYSTEMS: CASYS - FIRST INTERNATIONAL CONFERENCE, 1998, 437 : 606 - 625
  • [2] Unsupervised learning spectral functions with neural networks
    Wang, Lingxiao
    Shi, Shuzhe
    Zhou, Kai
    [J]. 28TH INTERNATIONAL NUCLEAR PHYSICS CONFERENCE, INPC 2022, 2023, 2586
  • [3] AN UNSUPERVISED LEARNING TECHNIQUE FOR ARTIFICIAL NEURAL NETWORKS
    ATIYA, AF
    [J]. NEURAL NETWORKS, 1990, 3 (06) : 707 - 711
  • [4] Unsupervised learning in LSTM recurrent neural networks
    Klapper-Rybicka, M
    Schraudolph, NN
    Schmidhuber, J
    [J]. ARTIFICIAL NEURAL NETWORKS-ICANN 2001, PROCEEDINGS, 2001, 2130 : 684 - 691
  • [5] UNSUPERVISED DYNAMIC LEARNING IN LAYERED NEURAL NETWORKS
    JONKER, HJJ
    COOLEN, ACC
    [J]. JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL, 1991, 24 (17): : 4219 - 4234
  • [6] Theories of neural networks leading to unsupervised learning
    Szu, Harold
    [J]. 2007 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-6, 2007, : 3121 - 3128
  • [7] Adaptive Learning Rate for Unsupervised Learning of Deep Neural Networks
    Golovko, Vladimir
    Mikhno, Egor
    Kroschanka, Aliaksandr
    Chodyka, Marta
    Lichograj, Piotr
    [J]. 2023 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, IJCNN, 2023,
  • [8] Variational approach to unsupervised learning algorithms of neural networks
    Likhovidov, V
    [J]. NEURAL NETWORKS, 1997, 10 (02) : 273 - 289
  • [9] Recursive Autoconvolution for Unsupervised Learning of Convolutional Neural Networks
    Knyazev, Boris
    Barth, Erhardt
    Martinetz, Thomas
    [J]. 2017 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2017, : 2486 - 2493
  • [10] Unsupervised learning in neural networks with short range synapses
    Brunnet, L. G.
    Agnes, E. J.
    Mizusaki, B. E. P.
    Erichsen, R., Jr.
    [J]. PHYSICS, COMPUTATION, AND THE MIND - ADVANCES AND CHALLENGES AT INTERFACES, 2013, 1510 : 251 - 254
12345