A New Feedforward Neural Network Structural Learning Algorithm—Augmentation by Training With Residuals

[+] Author and Article Information
C. James Li

Department of Mechanical Engineering, Aeronautical Engineering, and Mechanics, Rensselaer Polytechnic Institute, Troy, NY 12180-3590

Taehee Kim

Department of Mechanical Engineering, Columbia University, New York, N.Y. 10027

J. Dyn. Sys., Meas., Control 117(3), 411-415 (Sep 01, 1995) (5 pages) doi:10.1115/1.2799132 History: Received April 06, 1993; Online December 03, 2007


A fully automatic feedforward neural network structural and weight learning algorithm is described. The Augmentation by Training with Residuals, ATR, requires neither guess of initial weight values nor the number of neurons in the hidden layer from users. The algorithm takes an incremental approach in which a hidden neuron is trained to model the mapping between the input and output of current exemplars, and is augmented to the existing network. The exemplars are then made orthogonal to the newly identified hidden neuron and used for the training of next hidden neuron. The improvement continues until a desired accuracy is reached. This new structural and weight learning algorithm is applied to the identification of a two-degree-of-freedom planar robot, a Van der Pol oscillator and a Mackay-Glass equation. The algorithm is shown to be effective in modeling all three systems and is far superior to a linear modeling scheme in the case of the robot.

Copyright © 1995 by The American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.





Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In