Dynamical functional artificial neural network: Use of efficient piecewise linear functions

被引：0
|
作者：
Figueroa, J. L. [1 ]
Cousseau, J. E. [1 ]
机构：
[1] Univ Nacl Sur, CONICET, Dept Ingn Elect & Computadoras, RA-8000 Bahia Blanca, Buenos Aires, Argentina
来源：
LATIN AMERICAN APPLIED RESEARCH | 2008年 / 38卷 / 02期
关键词：
adaptive signal processing; nonlinear prediction; time series prediction;
D O I：
暂无
中图分类号：
TQ [化学工业];
学科分类号：
0817 ;
摘要：
A nonlinear adaptive time series predictor has been developed using a new type of piecewise linear (PWL) network for its underlying model structure. The PWL Network is a D-FANN (Dynamical Functional Artificial Neural Network) the activation functions of which are piecewise linear. The new realization is presented with the associated training algorithm. Properties and characteristics are discussed. This network has been successfully used to model and predict an important class of highly dynamic and non-stationary signals, namely speech signals.
引用
收藏
页码：187 / 193
页数：7
相关论文
共 50 条
  • [1] A piecewise linear dynamical functional artificial neural network (PWL-DFANN) for nonlinear adaptive time series prediction
    Figueroa, JL
    Cousseau, JE
    de Figueiredo, RJP
    2002 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOL I, PROCEEDINGS, 2002, : 29 - 32
  • [2] Dynamical stability conditions for recurrent neural networks with unsaturating piecewise linear transfer functions
    Wersing, H
    Beyn, WJ
    Ritter, H
    NEURAL COMPUTATION, 2001, 13 (08) : 1811 - 1825
  • [3] COMPUTATIONALLY SIMPLE NEURAL NETWORK APPROACH TO DETERMINE PIECEWISE-LINEAR DYNAMICAL MODEL
    Dolezel, P.
    Heckenbergerova, J.
    NEURAL NETWORK WORLD, 2017, 27 (04) : 351 - 371
  • [4] Hopfield neural network: The hyperbolic tangent and the piecewise-linear activation functions
    Mathias, Amanda C.
    Rech, Paulo C.
    NEURAL NETWORKS, 2012, 34 : 42 - 45
  • [5] Dynamical Behaviors of Multiple Equilibria in Competitive Neural Networks With Discontinuous Nonmonotonic Piecewise Linear Activation Functions
    Nie, Xiaobing
    Zheng, Wei Xing
    IEEE TRANSACTIONS ON CYBERNETICS, 2016, 46 (03) : 679 - 693
  • [6] COMPARISON OF A NEURAL NETWORK AND A PIECEWISE LINEAR CLASSIFIER
    LO, ZP
    BAVARIAN, B
    PATTERN RECOGNITION LETTERS, 1991, 12 (11) : 649 - 655
  • [7] An Efficient Algorithm for Representing Piecewise Linear Functions into Logic
    Preto, Sandro
    Finger, Marcelo
    ELECTRONIC NOTES IN THEORETICAL COMPUTER SCIENCE, 2020, 351 : 167 - 186
  • [8] Counter-example guided synthesis of neural network Lyapunov functions for piecewise linear systems
    Dai, Hongkai
    Landry, Benoit
    Pavone, Marco
    Tedrake, Russ
    2020 59TH IEEE CONFERENCE ON DECISION AND CONTROL (CDC), 2020, : 1274 - 1281
  • [9] Branch and bound for piecewise linear neural network verification
    Bunel, Rudy
    Turkaslan, Ilker
    Torr, Philip H.S.
    Pawan Kumar, M.
    Lu, Jingyue
    Kohli, Pushmeet
    1600, Microtome Publishing (21):
  • [10] Branch and Bound for Piecewise Linear Neural Network Verification
    Bunel, Rudy
    Turkaslan, Ilker
    Torr, Philip H. S.
    Kumar, M. Pawan
    Lu, Jingyue
    Kohli, Pushmeet
    JOURNAL OF MACHINE LEARNING RESEARCH, 2020, 21
12345