Neural network material model enhancement: Optimization through visualization and selective data removal

Jeremy N. Butkovich, Youssef M.A. Hashash

Research output: Contribution to journalConference articlepeer-review

Abstract

Neural network based constitutive models have recently been used to capture soil constitutive response. The neural networks are trained with large data sets. A novel method of enrichingthese training data sets is presented and tested, showing a limited data set can be expanded to a wider range of problems. A method of selectively reducing data set size is also presented, so that maximum behavior can be gleaned from a minimum amount of data. By using novel visualization techniques to evaluate the learned neural network model responses, it is shown that a large reduction in data set size does not significantly affect the performance of the neural network model.

Original languageEnglish (US)
Pages (from-to)2471-2480
Number of pages10
JournalGeotechnical Special Publication
Issue number130-142
StatePublished - Apr 25 2005
EventGeo-Frontiers 2005 - Austin, TX, United States
Duration: Jan 24 2005Jan 26 2005

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Architecture
  • Building and Construction
  • Geotechnical Engineering and Engineering Geology

Fingerprint Dive into the research topics of 'Neural network material model enhancement: Optimization through visualization and selective data removal'. Together they form a unique fingerprint.

Cite this