Evolutionary Design and Training of Artificial Neural Networks

被引：1

作者：

Kojecky, Lumir ^{[1
]}

Zelinka, Ivan ^{[1
]}

机构：

[1] VSB Tech Univ Ostrava, FEECS, Dept Comp Sci, 17 Listopadu 15, Ostrava 70833, Poruba, Czech Republic

来源：

ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, ICAISC 2018, PT I | 2018年 / 10841卷

基金：

欧盟地平线“2020”;

关键词：

Neural network synthesis; Network growth model; Complex network; Evolutionary algorithms;

D O I：

10.1007/978-3-319-91253-0_40

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The dynamics of neural networks and evolutionary algorithms share common attributes and based on many research papers it seems to be that from dynamic point of view are both systems indistinguishable. In order to compare them mutually from this point of view, artificial neural networks, as similar as possible to natural one, are needed. In this paper is described part of our research that is focused on the synthesis of artificial neural networks. Since most current ANN structures are not common in nature, we introduce a method of a complex network synthesis using network growth model, considered as a neural network. Synaptic weights of the synthesized ANN are then trained by an evolutionary algorithm to respond to an input training set successfully.

引用

页码：427 / 437

页数：11

共 50 条

[1] Evolutionary approach to design of Artificial Neural Networks
de Campos, LML
Roisenberg, M
de Campos, GAL
[J]. LOGIC, ARTIFICIAL INTELLIGENCE AND ROBOTICS, 2001, 7 : 35 - 42
[2] Evolutionary Artificial Bee Colony for Neural Networks Training
Ribeiro Serra Neto, Mario Tasso
Florenzano Mollinetti, Marco Antonio
Pereira, Rodrigo Lisboa
[J]. 2017 13TH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (ICNC-FSKD), 2017, : 44 - 49
[3] Hybrid multiobjective evolutionary design for artificial neural networks
Goh, Chi-Keong
Teoh, Eu-Jin
Tan, Kay Chen
[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS, 2008, 19 (09): : 1531 - 1548
[4] Evolutionary design of artificial neural networks with different nodes
Liu, Y
Yao, X
[J]. 1996 IEEE INTERNATIONAL CONFERENCE ON EVOLUTIONARY COMPUTATION (ICEC '96), PROCEEDINGS OF, 1996, : 670 - 675
[5] Artificial neural networks design using evolutionary algorithms
Castillo, PA
Arenas, MG
Castillo-Valdivieso, JJ
Merelo, JJ
Prieto, A
Romero, G
[J]. ADVANCES IN SOFT COMPUTING: ENGINEERING DESIGN AND MANUFACTURING, 2003, : 43 - 52
[6] Evolutionary training of artificial neural networks for radiotherapy treatment of cancers
Knowles, J
Corne, D
Bishop, M
[J]. 1998 IEEE INTERNATIONAL CONFERENCE ON EVOLUTIONARY COMPUTATION - PROCEEDINGS, 1998, : 398 - 403
[7] EVOLUTIONARY ARTIFICIAL NEURAL NETWORKS
Volna, Eva
[J]. MENDELL 2009, 2009, : 171 - 176
[8] Evolutionary artificial neural networks
Brown, AD
Card, HC
[J]. 1997 CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING, CONFERENCE PROCEEDINGS, VOLS I AND II: ENGINEERING INNOVATION: VOYAGE OF DISCOVERY, 1997, : 313 - 317
[9] ADANNET: Automatic design of artificial neural networks by evolutionary techniques
Barrios, D
Carrascal, A
Manrique, D
Rios, J
[J]. RESEARCH AND DEVELOPMENT IN INTELLIGENT SYSTEMS XVIII, 2002, : 67 - 80
[10] Evolutionary Artificial Neural Network Design and Training for wood veneer classification
Castellani, Marco
Rowlands, Hefin
[J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2009, 22 (4-5) : 732 - 741

← 1 2 3 4 5 →