Premium
Neural network approximation to nonlinear dynamics by velocity error backpropagation
Author(s) -
Ishii Hidenori,
Aiyoshi Eitaro
Publication year - 2002
Publication title -
electrical engineering in japan
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.136
H-Index - 28
eISSN - 1520-6416
pISSN - 0424-7760
DOI - 10.1002/eej.10011
Subject(s) - backpropagation , artificial neural network , computer science , nonlinear system , recurrent neural network , feed forward , feedforward neural network , artificial intelligence , algorithm , integrator , control theory (sociology) , physics , engineering , control engineering , control (management) , quantum mechanics , computer network , bandwidth (computing)
Abstract This paper presents a new type of recurrent neural network (RNN) and its learning algorithm for nonlinear dynamics, called “Velocity‐Error Backpropagation (VEBP).” In VEBP, learning is performed in two steps: (a) The velocity vector field of reference trajectories is approximated by a feedforward neural network (NN) with biconnection layers by backpropagating the velocity errors directly. (b) The RNN is constructed by adding integrators and output feedback loops to the trained feedforward NN. VEBP has some advantages over “backpropagation through time (BPTT),” the conventional learning method for RNNs. The effectiveness of the presented RNN and its learning algorithm is demonstrated by simulation results for some examples of nonlinear dynamics. © 2002 Wiley Periodicals, Inc. Electr Eng Jpn, 140(2): 26–35, 2002; Published online in Wiley InterScience ( www.interscience.wiley.com ). DOI 10.1002/eej.10011