Systematic and effective parameter and network tuning method by utilizing Jacobian rank deficiency

Guian Zhou, Jennie Si, Siming Lin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Most of neural network applications rely on the fundamental approximation property of feed-forward networks. In a realistic problem setting, a mechanism is needed to devise a learning process for implementing this approximate mapping based on available data, starting from choosing an appropriate set of parameters in order to avoid overfitting, to an efficient learning algorithm measured by computation and memory complexities, as well as the accuracy of the training procedure, and not to forget testing and cross-validation for generalization. In the present paper we develop a comprehensive procedure to address the above issues in a systematic manner. This process is based on a common observation of Jacobian rank deficiency. A new numerical procedure for solving the nonlinear optimization problem in supervised learning is introduced which not only reduces the training time and overall complexity but also achieves good training accuracy and generalization.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Symposium on Circuits and Systems
Editors Anon
PublisherIEEE
Pages597-600
Number of pages4
Volume1
StatePublished - 1997
EventProceedings of the 1997 IEEE International Symposium on Circuits and Systems, ISCAS'97. Part 4 (of 4) - Hong Kong, Hong Kong
Duration: Jun 9 1997Jun 12 1997

Other

OtherProceedings of the 1997 IEEE International Symposium on Circuits and Systems, ISCAS'97. Part 4 (of 4)
CityHong Kong, Hong Kong
Period6/9/976/12/97

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials

Fingerprint

Dive into the research topics of 'Systematic and effective parameter and network tuning method by utilizing Jacobian rank deficiency'. Together they form a unique fingerprint.

Cite this