Signal transmission in multilayer asynchronous neural networks

被引：0

作者：

Kobayashi, Wataru ^{[1
]}

Oku, Makito ^{[2
]}

Aihara, Kazuyuki ^{[1
,2
]}

机构：

[1] Univ Tokyo, Grad Sch Engn, Tokyo 1538505, Japan

[2] Univ Tokyo, Grad Sch Informat Sci & Technol, Tokyo 1538505, Japan

来源：

PROCEEDINGS OF THE SIXTEENTH INTERNATIONAL SYMPOSIUM ON ARTIFICIAL LIFE AND ROBOTICS (AROB 16TH '11) | 2011年

关键词：

Neural Networks; Asynchronous States; Active Decorrelation;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

It is believed that common input to nearby neurons leads to their synchronous spiking. However, recent studies have shown that recurrent neural networks can generate an asynchronous state characterized by low mean spiking correlations despite substantial amounts of shared input. The asynchronous state is generated by the interaction of excitatory and inhibitory populations, which is called active decorrelation. Here, we investigate the advantage of the active decorrelation on signal transmission in multilayer neural networks. The results of numerical simulations show that the active decorrelation is suitable for transmission of rate code because it can suppress the layer-by-layer growth of correlation.

引用

页码：334 / 337

页数：4

共 50 条

[31] Small signal and large signal modeling of HBT's using neural networks
Munshi, K
Vempada, P
Prasad, S
Sönmer, E
Schumacher, H
TELSIKS 2003: 6TH INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS IN MODERN SATELLITE, CABLE AND BROADCASTING SERVICE, VOLS 1 AND 2, PROCEEDINGS OF PAPERS, 2003, : 565 - 568
[32] An Approach for Recognition of Speech Signal Through Neural Networks
Sur, Chiranjib
2010 2ND INTERNATIONAL CONFERENCE ON COMPUTER AND AUTOMATION ENGINEERING (ICCAE 2010), VOL 1, 2010, : 215 - 217
[33] Tactile Sensor Signal Processing with Artificial Neural Networks
Guo, Bing
Qin, Lan
FUZZY INFORMATION AND ENGINEERING, VOL 1, 2009, 54 : 54 - 62
[34] Fast neural networks learning techniques for signal compression
Puchala, Dariusz
Yatsymirskyy, Mykhaylo
PRZEGLAD ELEKTROTECHNICZNY, 2010, 86 (01): : 189 - 191
[35] Adaptive neural networks for robust estimation of signal parameters
Lobos, T
Kostyla, P
Waclawek, Z
Cichocki, A
COMPEL-THE INTERNATIONAL JOURNAL FOR COMPUTATION AND MATHEMATICS IN ELECTRICAL AND ELECTRONIC ENGINEERING, 2000, 19 (03) : 903 - 912
[36] Training neural networks with additive noise in the desired signal
Wang, CA
Principe, JC
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (06): : 1511 - 1517
[37] Application of Wavelets and Neural Networks to Detect Weak Signal
Zhang, Wei
Ge, Linlin
2008 7TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION, VOLS 1-23, 2008, : 7000 - 7004
[38] A novel activation function for multilayer feed-forward neural networks
Aboubakar Nasser Samatin Njikam
Huan Zhao
Applied Intelligence, 2016, 45 : 75 - 82
[39] Use of multilayer feedforward neural networks in identification and control of Wiener model
AlDuwaish, H
Karim, MN
Chandrasekar, V
IEE PROCEEDINGS-CONTROL THEORY AND APPLICATIONS, 1996, 143 (03): : 255 - 258
[40] The quantization effects of different probability distribution on multilayer feedforward neural networks
Jiang, MH
Gielen, G
Deng, BX
Tang, XF
Ruan, QQ
Yuan, BZ
2002 6TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS I AND II, 2002, : 1175 - 1178

← 1 2 3 4 5 →