Discovering interpretable elastoplasticity models via the neural polynomial method enabled symbolic regressions
arXiv:2307.13149 · doi:10.1016/j.cma.2024.116827
Abstract
Conventional neural network elastoplasticity models are often perceived as lacking interpretability. This paper introduces a two-step machine learning approach that returns mathematical models interpretable by human experts. In particular, we introduce a surrogate model where yield surfaces are expressed in terms of a set of single-variable feature mappings obtained from supervised learning. A post-processing step is then used to re-interpret the set of single-variable neural network mapping functions into mathematical form through symbolic regression. This divide-and-conquer approach provides several important advantages. First, it enables us to overcome the scaling issue of symbolic regression algorithms. From a practical perspective, it enhances the portability of learned models for partial differential equation solvers written in different programming languages. Finally, it enables us to have a concrete understanding of the attributes of the materials, such as convexity and symmetries of models, through automated derivations and reasoning. Numerical examples have been provided, along with an open-source code to enable third-party validation.
References in corpus (7)
- Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
- The State of Sparsity in Deep Neural Networks
- What Does Explainable AI Really Mean? A New Conceptualization of Perspectives
- A new family of Constitutive Artificial Neural Networks towards automated model discovery
- Interpretable Machine Learning for Science with PySR and SymbolicRegression.jl
- Contemporary Symbolic Regression Methods and their Relative Performance
- Modeling assembly bias with machine learning and symbolic regression