Alternative learning vector quantization

被引：16

作者：

Wu, KL ^{[1
]}

Yang, MS

机构：

[1] Kun Shan Univ, Dept Informat Management, Tainan 71023, Taiwan

[2] Chung Yuan Christian Univ, Dept Appl Math, Chungli 32023, Taiwan

来源：

PATTERN RECOGNITION | 2006年 / 39卷 / 03期

关键词：

self-organizing map; learning vector quantization; competitive learning; learning rate; noise; outlier;

D O I：

10.1016/j.patcog.2005.09.011

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we discuss the influence of feature vectors contributions at each learning time t on a sequential-type competitive learning algorithm. We then give a learning rate annealing schedule to improve the unsupervised teaming vector quantization (ULVQ) algorithm which uses the winner-take-all competitive learning principle in the self-organizing map (SOM). We also discuss the noisy and outlying problems of a sequential competitive learning algorithm and then propose an alternative learning formula to make the sequential competitive teaming robust to noise and outliers. Combining the proposed learning rate annealing schedule and alternative teaming formula, we propose an alternative learning vector quantization (ALVQ) algorithm. Some discussion and experimental results from comparing ALVQ with ULVQ show the superiority of the proposed method. (c) 2005 Pattern Recognition Society. Published by Elsevier Ltd. All rights reserved.

引用

页码：351 / 362

页数：12

共 50 条

[11] Distance Learning in Discriminative Vector Quantization
Schneider, Petra
Biehl, Michael
Hammer, Barbara
NEURAL COMPUTATION, 2009, 21 (10) : 2942 - 2969
[12] Differential privacy for learning vector quantization
Brinkrolf, Johannes
Goepfert, Christina
Hammer, Barbara
NEUROCOMPUTING, 2019, 342 : 125 - 136
[13] Generalized relevance learning vector quantization
Hammer, B
Villmann, T
NEURAL NETWORKS, 2002, 15 (8-9) : 1059 - 1068
[14] The improvements of the learning vector quantization method
Yokoo, T
Nagasaka, K
ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3, 1998, : 542 - 545
[15] Learning vector quantization for multimodal data
Hammer, B
Strickert, M
Villmann, T
ARTIFICIAL NEURAL NETWORKS - ICANN 2002, 2002, 2415 : 370 - 376
[16] sklvq: Scikit Learning Vector Quantization
van Veen, Rick
Biehl, Michael
De Vries, Gert-Jan
JOURNAL OF MACHINE LEARNING RESEARCH, 2021, 22
[17] Robust vector quantization by competitive learning
Buhmann, JM
Hofmann, T
1997 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I - V: VOL I: PLENARY, EXPERT SUMMARIES, SPECIAL, AUDIO, UNDERWATER ACOUSTICS, VLSI; VOL II: SPEECH PROCESSING; VOL III: SPEECH PROCESSING, DIGITAL SIGNAL PROCESSING; VOL IV: MULTIDIMENSIONAL SIGNAL PROCESSING, NEURAL NETWORKS - VOL V: STATISTICAL SIGNAL AND ARRAY PROCESSING, APPLICATIONS, 1997, : 139 - 142
[18] Relational Extensions of Learning Vector Quantization
Hammer, Barbara
Schleif, Frank-Michael
Zhu, Xibin
NEURAL INFORMATION PROCESSING, PT II, 2011, 7063 : 481 - 489
[19] Noise Fuzzy Learning Vector Quantization
Wu, Xiao-Hong
Wu, Bin
Zhao, Jie-Wen
ADVANCED MEASUREMENT AND TEST, PARTS 1 AND 2, 2010, 439-440 : 367 - +
[20] EEG CLASSIFICATION BY LEARNING VECTOR QUANTIZATION
FLOTZINGER, D
KALCHER, J
PFURTSCHELLER, G
BIOMEDIZINISCHE TECHNIK, 1992, 37 (12): : 303 - 309

← 1 2 3 4 5 →