Comparing hybrid systems to design and optimize artificial neural networks

被引:0
|
作者
Castillo, PA [1 ]
Arenas, MG [1 ]
Merelo, JJ [1 ]
Romero, G [1 ]
Rateb, F [1 ]
Prieto, A [1 ]
机构
[1] Univ Granada, Dept Architecture & Comp Technol, E-18071 Granada, Spain
来源
关键词
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
In this paper we conduct a comparative study between hybrid methods to optimize multilayer perceptrons: a model that optimizes the architecture and initial weights of multilayer perceptrons; a parallel approach to optimize the architecture and initial weights of multilayer perceptrons; a method that searches for the parameters of the training algorithm, and an approach for cooperative co-evolutionary optimization of multilayer perceptrons. Obtained results show that a co-evolutionary model obtains similar or better results than specialized approaches, needing much less training epochs and thus using much less simulation time.
引用
收藏
页码:240 / 249
页数:10
相关论文
共 50 条
  • [1] 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
  • [2] Hybrid heuristics for optimal design of Artificial Neural Networks
    Abraham, A
    Nath, B
    [J]. DEVELOPMENTS IN SOFT COMPUTING, 2001, : 15 - 22
  • [3] HYBRID OPTIMIZATION TECHNIQUE FOR ARTIFICIAL NEURAL NETWORKS DESIGN
    Zanchettin, Cleber
    Ludermir, Teresa B.
    [J]. ICEIS 2009 : PROCEEDINGS OF THE 11TH INTERNATIONAL CONFERENCE ON ENTERPRISE INFORMATION SYSTEMS, VOL AIDSS, 2009, : 242 - 247
  • [4] Artificial neural networks to optimize the extrusion of an aluminium alloy
    Lucignano, Carmine
    Montanari, Roberto
    Tagliaferri, Vincenzo
    Ucciardello, Nadia
    [J]. JOURNAL OF INTELLIGENT MANUFACTURING, 2010, 21 (04) : 569 - 574
  • [5] Artificial neural networks to optimize the extrusion of an aluminium alloy
    Carmine Lucignano
    Roberto Montanari
    Vincenzo Tagliaferri
    Nadia Ucciardello
    [J]. Journal of Intelligent Manufacturing, 2010, 21 : 569 - 574
  • [6] Design of Analog and Digital Hybrid MAC Circuit for Artificial Neural Networks
    Park, Ki-Hyuk
    Cho, Min-Hyung
    Jeon, Young-Deuk
    Lee, Joo-Hyun
    [J]. 2019 INTERNATIONAL CONFERENCE ON ELECTRONICS, INFORMATION, AND COMMUNICATION (ICEIC), 2019, : 509 - 511
  • [7] Artificial neural networks: a promising tool to design and optimize high-pressure food processes
    Torrecilla, JS
    Otero, L
    Sanz, PD
    [J]. JOURNAL OF FOOD ENGINEERING, 2005, 69 (03) : 299 - 306
  • [8] APPLICATION OF ARTIFICIAL NEURAL NETWORKS IN STRUCTURAL DESIGN EXPERT-SYSTEMS
    MUKHERJEE, A
    DESHPANDE, JM
    [J]. COMPUTERS & STRUCTURES, 1995, 54 (03) : 367 - 375
  • [9] Artificial neural networks for design of manufacturing systems and selection of priority rules
    Çakar, T
    Cil, I
    [J]. INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING, 2004, 17 (03) : 195 - 211
  • [10] Application of artificial neural networks to the design and implementation of electronic olfactory systems
    Brezmes, J
    Canyellas, N
    Llobet, E
    Vilanova, X
    Correig, X
    [J]. BIOLOGICAL AND ARTIFICIAL COMPUTATION: FROM NEUROSCIENCE TO TECHNOLOGY, 1997, 1240 : 1183 - 1192