Self-organizing maps with dynamic learning for signal reconstruction

被引：4

作者：

Cho, Jeongho ^{[1
]}

Paiva, Antonio R. C. ^{[1
]}

Kim, Sung-Phil ^{[1
]}

Sanchez, Justin C. ^{[1
]}

Principe, Jose C. ^{[1
]}

机构：

[1] Univ Florida, Computat NeuroEngn Lab, Gainesville, FL 32611 USA

来源：

NEURAL NETWORKS | 2007年 / 20卷 / 02期

关键词：

spike reconstruction; self-organizing map; brain-machine interface; vector quantization;

D O I：

10.1016/j.neunet.2006.12.002

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Wireless Brain Machine Interface (BMI) communication protocols are faced with the challenge of transmitting the activity of hundreds of neurons which requires large bandwidth. Previously a data compression scheme for neural activity was introduced based on Self Organizing Maps (SOM). In this paper we propose a dynamic learning rule for improved training of the SOM on signals with sparse events which allows for more representative prototype vectors to be found, and consequently better signal reconstruction. This work was developed with BMI applications in mind and therefore our examples are geared towards this type of signals. The simulation results show that the proposed strategy outperforms conventional vector quantization methods for spike reconstruction. (c) 2006 Elsevier Ltd. All rights reserved.

引用

页码：274 / 284

页数：11

共 50 条

[1] Learning self-organizing maps for navigation in dynamic worlds
Araújo, R
Gouveia, G
Santos, N
2003 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS 1-3, PROCEEDINGS, 2003, : 1312 - 1317
[2] Dynamic Formation of Self-Organizing Maps
Fix, Jeremy
ADVANCES IN SELF-ORGANIZING MAPS AND LEARNING VECTOR QUANTIZATION, 2014, 295 : 25 - 34
[3] Incremental learning with self-organizing maps
Gepperth, Alexander
Karaoguz, Cem
2017 12TH INTERNATIONAL WORKSHOP ON SELF-ORGANIZING MAPS AND LEARNING VECTOR QUANTIZATION, CLUSTERING AND DATA VISUALIZATION (WSOM), 2017, : 153 - 160
[4] Learning metrics for self-organizing maps
Kaski, S
Sinkkonen, J
Peltonen, J
IJCNN'01: INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-4, PROCEEDINGS, 2001, : 914 - 919
[5] Active learning in self-organizing maps
Hasenjäger, M
Ritter, H
Obermayer, K
KOHONEN MAPS, 1999, : 57 - 70
[6] Sensor Signal Clustering with Self-Organizing Maps
Popovici, Razvan
Andonie, Razvan
2015 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2015,
[7] Dynamic growing self-organizing maps for surface reconstruction from point clouds
Zhang, Yue
Dai, Ning
Liu, Hao
Li, Dawei
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2016, 28 (09): : 1489 - 1496
[8] Self-organizing maps with information theoretic learning
Chalasani, Rakesh
Principe, Jose C.
NEUROCOMPUTING, 2015, 147 : 3 - 14
[9] Rapid learning with parametrized self-organizing maps
Walter, J
Ritter, H
NEUROCOMPUTING, 1996, 12 (2-3) : 131 - 153
[10] Multiple self-organizing maps for supervised learning
Cervera, E
delPobil, AP
FROM NATURAL TO ARTIFICIAL NEURAL COMPUTATION, 1995, 930 : 345 - 352

← 1 2 3 4 5 →