Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

A Systematic and Effective Supervised Learning Mechanism Based on Jacobian Rank Deficiency

A Systematic and Effective Supervised Learning Mechanism Based on Jacobian Rank Deficiency Most neural network applications rely on the fundamental approximation property of feedforward networks. Supervised learning is a means of implementing this approximate mapping. In a realistic problem setting, a mechanism is needed to devise this learning process based on available data, which encompasses choosing an appropriate set of parameters in order to avoid overfitting, using an efficient learning algorithm measured by computation and memory complexities, ensuring the accuracy of the training procedure as measured by the training error, and testing and cross-validation for generalization. We develop a comprehensive supervised learning algorithm to address these issues. The algorithm combines training and pruning into one procedure by utilizing a common observation of Jacobian rank deficiency in feedforward networks. The algorithm not only reduces the training time and overall complexity but also achieves training accuracy and generalization capabilities comparable to more standard approaches. Extensive simulation results are provided to demonstrate the effectiveness of the algorithm. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Neural Computation MIT Press

A Systematic and Effective Supervised Learning Mechanism Based on Jacobian Rank Deficiency

Zhou, Guian; Si, Jennie
Neural Computation , Volume 10 (4) – May 15, 1998
Download PDF
15 pages

Loading next page...
 
/lp/mit-press/a-systematic-and-effective-supervised-learning-mechanism-based-on-nh2n8oxy4l

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
MIT Press
Copyright
© 1998 Massachusetts Institute of Technology
ISSN
0899-7667
eISSN
1530-888X
DOI
10.1162/089976698300017610
Publisher site
See Article on Publisher Site

Abstract

Most neural network applications rely on the fundamental approximation property of feedforward networks. Supervised learning is a means of implementing this approximate mapping. In a realistic problem setting, a mechanism is needed to devise this learning process based on available data, which encompasses choosing an appropriate set of parameters in order to avoid overfitting, using an efficient learning algorithm measured by computation and memory complexities, ensuring the accuracy of the training procedure as measured by the training error, and testing and cross-validation for generalization. We develop a comprehensive supervised learning algorithm to address these issues. The algorithm combines training and pruning into one procedure by utilizing a common observation of Jacobian rank deficiency in feedforward networks. The algorithm not only reduces the training time and overall complexity but also achieves training accuracy and generalization capabilities comparable to more standard approaches. Extensive simulation results are provided to demonstrate the effectiveness of the algorithm.

Journal

Neural Computation – MIT Press

Published: May 15, 1998

There are no references for this article.