Feed-forward Neural Networks with Trainable Delay

被引：0
|
作者：
Ji, Xunbi A. [1 ]
Molnar, Tamas G. [1 ]
Avedisov, Sergei S. [1 ,2 ]
Orosz, Gabor [1 ]
机构：
[1] Univ Michigan, Dept Mech Engn, Ann Arbor, MI 48109 USA
[2] Toyota Motor North Amer R&D Infotech Labs, Mountain View, CA 94043 USA
来源：
LEARNING FOR DYNAMICS AND CONTROL, VOL 120 | 2020年 / 120卷
关键词：
delayed feed-forward neural network; car-following; connected automated vehicle; time delay system;
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：
In this paper we build a bridge between feed-forward neural networks and delayed dynamical systems. As an initial demonstration, we capture the car-following behavior of a connected automated vehicle that includes time delay by using both simulation data and experimental data. We construct a delayed feed-forward neural network (DFNN) and introduce a training algorithm in order to learn the delay. We demonstrate that this algorithm works well on the proposed structures.
引用
收藏
页码：127 / 136
页数：10
相关论文
共 50 条
  • [41] Distributed Restoration in Optical Networks using Feed-forward Neural Networks
    Demeter Gokisik Karpat
    Semih Bilgen
    Photonic Network Communications, 2006, 12 (1)
  • [42] Exploring Edge TPU for deep feed-forward neural networks
    Hosseininoorbin, Seyedehfaezeh
    Layeghy, Siamak
    Kusy, Brano
    Jurdak, Raja
    Portmann, Marius
    INTERNET OF THINGS, 2023, 22
  • [43] Classification of urinary calculi using feed-forward neural networks
    Kuzmanovski, I
    Zdravkova, K
    Trpkovska, M
    SOUTH AFRICAN JOURNAL OF CHEMISTRY-SUID-AFRIKAANSE TYDSKRIF VIR CHEMIE, 2006, 59 : 12 - 16
  • [44] A novel activation function for multilayer feed-forward neural networks
    Aboubakar Nasser Samatin Njikam
    Huan Zhao
    Applied Intelligence, 2016, 45 : 75 - 82
  • [45] Probabilistic and statistical aspects of feed-forward nonlinear neural networks
    Koshimizu, T
    Tsujitani, M
    ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3, 1998, : 490 - 493
  • [46] Universal approximation of fully complex feed-forward neural networks
    Kim, T
    Adali, H
    2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 973 - 976
  • [47] Dynamic hysteresis modelling using feed-forward neural networks
    Makaveev, D
    Dupré, L
    De Wulf, M
    Melkebeek, J
    JOURNAL OF MAGNETISM AND MAGNETIC MATERIALS, 2003, 254 : 256 - 258
  • [48] Intelligent process modelling using Feed-Forward Neural Networks
    Gadallah M.H.
    Hamid El-Sayed K.A.
    Hekman K.
    International Journal of Manufacturing Technology and Management, 2010, 19 (3-4) : 238 - 257
  • [49] Training Algorithm with Incomplete Data for Feed-Forward Neural Networks
    Song-Yee Yoon
    Soo-Young Lee
    Neural Processing Letters, 1999, 10 : 171 - 179
  • [50] A novel activation function for multilayer feed-forward neural networks
    Njikam, Aboubakar Nasser Samatin
    Zhao, Huan
    APPLIED INTELLIGENCE, 2016, 45 (01) : 75 - 82
12345