Parallel implementation of self-organizing map on the partial tree shape neurocomputer

被引：7

作者：

Kolinummi, P ^{[1
]}

Pulkkinen, P ^{[1
]}

Hämäläinen, T ^{[1
]}

Saarinen, J ^{[1
]}

机构：

[1] Tampere Univ Technol, Signal Proc Lab, FIN-33720 Tampere, Finland

来源：

NEURAL PROCESSING LETTERS | 2000年 / 12卷 / 02期

基金：

芬兰科学院;

关键词：

computer architecture; neurocomputer; parallel hardware implementation; parallel mapping; self-organizing map;

D O I：

10.1023/A:1009665814041

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A parallel mapping of self-organizing map (SOM) algorithm is presented for a partial tree shape neurocomputer (PARNEU). PARNEU is a general purpose parallel neurocomputer that is designed for soft computing applications. Practical scalability and a reconfigurable partial tree network are the main architectural features. The presented neuron parallel mapping of SOM with on-line learning illustrates a parallel winner neuron search and a coordinate transfer that are performed in the partial tree network. Phase times are measured to analyse speedup and scalability of the mapping. The performance of the learning phase in SOM with a four processor PARNEU configuration is about 26 MCUPS and the recall phase performs 30 MCPS. Compared to other mappings done for general purpose neurocomputers, PARNEU's performance is very good.

引用

页码：171 / 182

页数：12

共 50 条

[11] Parallel implementation of handwritten digit recognition system using self-organizing map
Wang, Yi-Mu
Pan, Yun
Long, Yan-Chen
Yan, Xiao-Lang
Huan, Ruo-Hong
Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science), 2014, 48 (04): : 742 - 747
[12] Parallel FPGA implementation of self-organizing maps
Ben Khalifa, K
Girau, B
Alexandre, F
Bedoui, MH
16TH INTERNATIONAL CONFERENCE ON MICROELECTRONICS, PROCEEDINGS, 2004, : 709 - 712
[13] Binary tree time adaptive self-organizing map
Shah-Hosseini, Hamed
NEUROCOMPUTING, 2011, 74 (11) : 1823 - 1839
[14] Self-organizing tree map approach for image segmentation
Kong, HS
Guan, L
Kung, SY
2002 6TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I AND II, 2002, : 588 - 591
[15] A parallel general implementation of Kohonen's self-organizing map algorithm: performance and scalability
Ozdzynski, P
Lin, A
Liljeholm, M
Beatty, J
NEUROCOMPUTING, 2002, 44 : 567 - 571
[16] A growing parallel self-organizing map for unsupervised learning
Valova, I
Szer, D
Georgieva, N
PROCEEDING OF THE 2002 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-3, 2002, : 1924 - 1929
[17] A Binary Self-Organizing Map and its FPGA Implementation
Appiah, Kofi
Hunter, Andrew
Meng, Hongying
Yue, Shigang
Hobden, Mervyn
Priestley, Nigel
Hobden, Peter
Pettit, Cy
IJCNN: 2009 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1- 6, 2009, : 2918 - +
[18] FPGA Based Hardware Implementation of a Self-Organizing Map
Brassai, S. T.
2014 18TH INTERNATIONAL CONFERENCE ON INTELLIGENT ENGINEERING SYSTEMS (INES), 2014, : 101 - 104
[19] Hardware Implementation of Deep Self-organizing Map Networks
Tanaka, Yuichiro
Tamukoh, Hakaru
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2017, PT I, 2017, 10613 : 439 - 441
[20] The self-organizing map
Kohonen, T
NEUROCOMPUTING, 1998, 21 (1-3) : 1 - 6

← 1 2 3 4 5 →