Neural network material model enhancement: Optimization through selective data removal

Abstract

Neural network ~NN!-based constitutive models have been used increasingly to capture soil constitutive response. When combined with the self-learning simulation ~SelfSim! inverse analysis framework, NN models can be used to extract soil behavior when given field measurements of boundary deformations and loads. However, the data sets used to train and… (More)
DOI: 10.1017/S089006040707014X

Topics

16 Figures and Tables

Slides referencing similar topics