Artificial neural networks with input gates

被引：0

作者：

Murata, J ^{[1
]}

Noda, T ^{[1
]}

Hirasawa, K ^{[1
]}

机构：

[1] Kyushu Univ, Dept Elect & Elect Syst Engn, Fukuoka 8128581, Japan

来源：

IEEE WORLD CONGRESS ON COMPUTATIONAL INTELLIGENCE | 1998年

关键词：

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：

An architecture of multi-layer neural networks is proposed. The networks are equipped with gates on their input channels in order to control the flow of input signals. A gate on an input channel opens and closes depending on the current values of the other input signals. The dependency is automatically determined based on training data. These gates give the networks a good generalization ability because they can eliminate harmful inputs. Also they can indicate which input is significant in which situations, and therefore they provide us with an insight into the input-output relationship underlying the training data.

引用

页码：480 / 485

页数：6

共 50 条

[41] Artificial Neural Networks Predicting the Outcome of a Throwing Task - Effects of Input Quantity and Quality
Joch, Michael
Jaeger, Joerg M.
Maurer, Heiko
Maurer, Lisa K.
Mueller, Hermann
PROCEEDINGS OF THE 11TH INTERNATIONAL SYMPOSIUM ON COMPUTER SCIENCE IN SPORT (IACSS 2017), 2018, 663 : 23 - 34
[42] Audio environment classification for hearing aids using artificial neural networks with windowed input
Freeman, C.
Dony, R. D.
Areibi, S. M.
2007 IEEE SYMPOSIUM ON COMPUTATIONAL INTELLIGENCE IN IMAGE AND SIGNAL PROCESSING, 2007, : 183 - 188
[43] LICON: A Linear Weighting Scheme for the Contribution of Input Variables in Deep Artificial Neural Networks
Kasneci, Gjergji
Gottron, Thomas
CIKM'16: PROCEEDINGS OF THE 2016 ACM CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, 2016, : 45 - 54
[44] Impact of Selected Input Features for Lightpath Feasibility Validation Using Artificial Neural Networks
Morais, Rui Manuel
Pedro, Joao
2018 20TH ANNIVERSARY INTERNATIONAL CONFERENCE ON TRANSPARENT OPTICAL NETWORKS (ICTON), 2018,
[45] Artificial Neural Networks manipulation server:: Research on the integration of databases and Artificial Neural Networks
Santos, A
Arcay, B
Dorado, J
Rodríguez, AB
Pazos, A
NEURAL COMPUTING & APPLICATIONS, 2002, 11 (01): : 3 - 16
[46] Performance of artificial neural networks and genetical evolved artificial neural networks unfolding techniques
Ortiz-Rodriguez, J. M.
Martinez-Blanco, M. R.
Vega-Carrillo, H. R.
Gallego Diaz, E.
Lorente Fillol, A.
Mendez Villafane, R.
Los Arcos Merino, J. M.
Guerrero Araque, J. E.
REVISTA MEXICANA DE FISICA, 2011, 57 (01) : 89 - 92
[47] Artificial Neural Networks Manipulation Server: Research on the Integration of Databases and Artificial Neural Networks
A. Santos
B. Arcay
J. Dorado
A.B. Rodríguez
A. Pazos
Neural Computing & Applications, 2002, 11 : 3 - 16
[48] Artificial neural networks in power systems Part 2 Types of artificial neural networks
Aggarwal, R
Song, Y
POWER ENGINEERING JOURNAL, 1998, 12 (01): : 41 - 47
[49] Input selection and optimisation for monthly rainfall forecasting in Queensland, Australia, using artificial neural networks
Abbot, John
Marohasy, Jennifer
ATMOSPHERIC RESEARCH, 2014, 138 : 166 - 178
[50] Selection of input features across subjects for classifying crewmember workload using artificial neural networks
Laine, TI
Bauer, KW
Lanning, JW
Russell, CA
Wilson, GF
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART A-SYSTEMS AND HUMANS, 2002, 32 (06): : 691 - 704

← 1 2 3 4 5 →