Neural network approximation to nonlinear dynamics by velocity error backpropagation

Hidenori Ishii, Eitaro Aiyoshi

研究成果: Article

抜粋

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.

元の言語English
ページ(範囲)26-35
ページ数10
ジャーナルElectrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi)
140
発行部数2
DOI
出版物ステータスPublished - 2002 7 30

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

フィンガープリント Neural network approximation to nonlinear dynamics by velocity error backpropagation' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用