Neural network architectures: New strategies for real time problems

被引：0
|
作者：
Ugena, A [1 ]
De Arriaga, F [1 ]
El Alami, M [1 ]
机构：
[1] Univ Politecn Madrid, Escuela TS Ingn Telecommun, E-28040 Madrid, Spain
来源：
INTERNATIONAL CONFERENCE ON COMPUTING AND INFORMATION TECHNOLOGIES : EXPLORING EMERGING TECHNOLOGIES | 2001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：
There are a few rules to design neural networks most of them coming from experience. In the case of functional-link neural networks it is even worst because they are not well known in spite of their advantages which make them suitable for real time problems. To void the intuition-inspired design some strategies related to very well known mathematical techniques are proposed. They have been used for the solution of a real time problem: speech recognition. The obtained results, from which only a sample has been included, show drastic reductions in the iteration number to reduce the error under a certain bound and an increase of the learning rate.
引用
收藏
页码：247 / 253
页数：7
相关论文
共 50 条
  • [1] Real-Time Scheduling on Heterogeneous SoC Architectures Using A Neural Network
    Chillet, Daniel
    Pillement, Sebastien
    Sentieys, Olivier
    TRAITEMENT DU SIGNAL, 2009, 26 (01) : 77 - 89
  • [2] A neural network model for real-time scheduling on heterogeneous SoC architectures
    Chillet, Daniel
    Pillement, Sebastien
    Sentieys, Olivier
    2007 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-6, 2007, : 102 - +
  • [3] Real time services in IP network architectures
    Gilardi, A
    BROADBAND STRATEGIES AND TECHNOLOGIES FOR WIDE AREA AND LOCAL ACCESS NETWORKS, 1996, 2953 : 89 - 97
  • [4] Real-time interface model for neural architectures
    Signorini, Jacqueline
    Neural Networks, 1988, 1 (1 SUPPL)
  • [5] Real-time CVSA decals recognition system using deep convolutional neural network architectures
    Yepez, Juan
    Castro-Zunti, Riel
    Choi, Younhee
    Ko, Seok-Bum
    IET INTELLIGENT TRANSPORT SYSTEMS, 2021, 15 (11) : 1359 - 1371
  • [6] INTERFACING REAL-TIME DATA STREAMS FOR NEURAL ARCHITECTURES
    SIGNORINI, J
    NEURAL NETWORKS FROM MODELS TO APPLICATIONS, 1989, : 673 - 681
  • [7] A Neural Network Model for Solving Nonlinear Optimization Problems with Real-Time Applications
    Malek, Alaeddin
    Yashtini, Maryam
    ADVANCES IN NEURAL NETWORKS - ISNN 2009, PT 3, PROCEEDINGS, 2009, 5553 : 98 - 108
  • [8] Discrete time recurrent neural network architectures: A unifying review
    Tsoi, AC
    Back, A
    NEUROCOMPUTING, 1997, 15 (3-4) : 183 - 223
  • [9] Discrete time recurrent neural network architectures: A unifying review
    Faculty of Informatics, University of Wollongong, Northfields Ave., Wollongong, NSW 2522, Australia
    NEUROCOMPUTING, 3-4 (183-223):
  • [10] Parallelizing Convolutional Neural Network for the Handwriting Recognition Problems with Different Architectures
    Zhou, Junhao
    Chen, Weibin
    Peng, Guishen
    Xiao, Hong
    Wang, Hao
    Chen, Zhigang
    PROCEEDINGS OF 2017 IEEE INTERNATIONAL CONFERENCE ON PROGRESS IN INFORMATICS AND COMPUTING (PIC 2017), 2017, : 71 - 76
12345