Context quantization and contextual self-organizing maps

被引：12
|
作者：
Voegtlin, T [1 ]
机构：
[1] CNRS, UPR 9075, Inst Cognit Sci, F-69365 Lyon, France
来源：
IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL VI | 2000年
关键词：
D O I：
10.1109/IJCNN.2000.859367
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Vector quantization consists in finding a discrete approximation of a continuous input. One of the most popular neural algorithms related to vector quantization is the, so called, Kohonen map. In this paper we generalize vector quantization to temporal data, introducing context quantization. We propose a recurrent network inspired by the Kohonen map, the Contextual Self-Organizing Map, that develops near-optimal representations of context. We demonstrate quantitatively that this algorithm shows better performance than the other neural methods proposed so far.
引用
收藏
页码：20 / 25
页数：6
相关论文
共 50 条
  • [1] Self-organizing maps, vector quantization, and mixture modeling
    Heskes, T
    [J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12 (06): : 1299 - 1305
  • [2] On the use of self-organizing maps to accelerate vector quantization
    de Bodt, E
    Cottrell, M
    Letremy, P
    Verleysen, M
    [J]. NEUROCOMPUTING, 2004, 56 : 187 - 203
  • [3] Vector Quantization of Speech Frames Based on Self-Organizing Maps
    Simoes, Flavio Olmos
    Neto, Mario Uliani
    Machado, Jeremias Barbosa
    Nagle, Edson Jose
    Runstein, Fernando Oscar
    Teixeira Gomes, Leandro de Campos
    [J]. BRAIN INSPIRED COGNITIVE SYSTEMS 2008, 2010, 657 : 201 - 216
  • [4] Stability Analysis of Self-Organizing Maps and Vector Quantization Algorithms
    Tucci, Mauro
    Raugi, Marco
    [J]. 2010 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS IJCNN 2010, 2010,
  • [5] Limitations of self-organizing maps for vector quantization and multidimensional scaling
    Flexer, A
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 9: PROCEEDINGS OF THE 1996 CONFERENCE, 1997, 9 : 445 - 451
  • [6] Kohonen's self-organizing maps in contextual analysis of data
    Honkela, T
    Koskinen, I
    Koskenniemi, T
    Karvonen, S
    [J]. INFORMATION ORGANIZATION AND DATABASES: FOUNDATIONS OF DATA ORGANIZATION, 2000, 579 : 135 - 148
  • [7] Self-Organizing Maps and Learning Vector Quantization for Feature Sequences
    Panu Somervuo
    Teuvo Kohonen
    [J]. Neural Processing Letters, 1999, 10 : 151 - 159
  • [8] Self-organizing maps and learning vector quantization for feature sequences
    Somervuo, P
    Kohonen, T
    [J]. NEURAL PROCESSING LETTERS, 1999, 10 (02) : 151 - 159
  • [9] Self-Organizing Maps
    Matera, F
    [J]. SUBSTANCE USE & MISUSE, 1998, 33 (02) : 365 - 381
  • [10] Controlling the asymptotic level density for quantization processes with self-organizing maps
    Skubalska-Rafajlowicz, E
    [J]. NEURAL NETWORKS AND SOFT COMPUTING, 2003, : 638 - 643
12345