Training partially recurrent neural networks using evolutionary strategies

被引：21
|
作者：
Greenwood, GW
机构：
[1] Department of Electrical and Computer Engineering, Western Michigan University, Kalamazoo
来源：
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING | 1997年 / 5卷 / 02期
关键词：
D O I：
10.1109/89.554781
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
This correspondence presents the latest results of using evolutionary strategies (ES's) to design partially recurrent neural networks for viseme recognition. ES's are stochastic optimization algorithms based upon the principles of natural selection found in the biological world. Our results indicate that ES's can be effectively used to determine the synaptic weights in neural networks and can outperform backpropagation techniques.
引用
收藏
页码：192 / 194
页数：3
相关论文
共 50 条
  • [1] Solving evolutionary problems using recurrent neural networks
    Petrasova, Iveta
    Karban, Pavel
    [J]. JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS, 2023, 426
  • [2] Evolutionary approach to training feed-forward and recurrent neural networks
    Riley, Jeff
    Ciesielski, Victor B.
    [J]. International Conference on Knowledge-Based Intelligent Electronic Systems, Proceedings, KES, 1998, 3 : 596 - 602
  • [3] Identification of electrical loads using partially recurrent neural networks
    Franklin, DRC
    Morelato, A
    [J]. 4TH WORLD CONGRESS OF EXPERT SYSTEMS, VOL 1 AND 2: APPLICATION OF ADVANCED INFORMATION TECHNOLOGIES, 1998, : 842 - 847
  • [4] Training recurrent neural networks using a hybrid algorithm
    Mounir Ben Nasr
    Mohamed Chtourou
    [J]. Neural Computing and Applications, 2012, 21 : 489 - 496
  • [5] Training recurrent neural networks using a hybrid algorithm
    Ben Nasr, Mounir
    Chtourou, Mohamed
    [J]. NEURAL COMPUTING & APPLICATIONS, 2012, 21 (03): : 489 - 496
  • [6] Evolutionary Training of Hybrid Systems of Recurrent Neural Networks and Hidden Markov Models
    Chandra, Rohitash
    Omlin, Christian W.
    [J]. PROCEEDINGS OF WORLD ACADEMY OF SCIENCE, ENGINEERING AND TECHNOLOGY, VOL 15, 2006, 15 : 58 - +
  • [7] An evolutionary approach to training feed-forward and recurrent neural networks.
    Riley, J
    Ciesielski, VB
    [J]. 1998 SECOND INTERNATIONAL CONFERENCE ON KNOWLEDGE-BASED INTELLIGENT ELECTRONIC SYSTEMS, KES '98, PROCEEDINGS, VOL, 3, 1998, : 596 - 602
  • [8] Evolutionary algorithms for training neural networks
    Mohan, Chilukuri K.
    [J]. MODELING AND SIMULATION FOR MILITARY APPLICATIONS, 2006, 6228
  • [9] Constructive training of recurrent neural networks using hybrid optimization
    Subrahmanya, Niranjan
    Shin, Yung C.
    [J]. NEUROCOMPUTING, 2010, 73 (13-15) : 2624 - 2631
  • [10] Problems and features of evolutionary algorithms to build hybrid training methods for recurrent neural networks
    Cuellar, M. P.
    Delgado, M.
    Pegalajar, M. C.
    [J]. ICEIS 2007: PROCEEDINGS OF THE NINTH INTERNATIONAL CONFERENCE ON ENTERPRISE INFORMATION SYSTEMS: ARTIFICIAL INTELLIGENCE AND DECISION SUPPORT SYSTEMS, 2007, : 204 - 211
12345