Explainable Hierarchical Deep Learning Neural Networks (Ex-HiDeNN)

TL;DR

Ex-HiDeNN is a novel neural network approach that combines hierarchical deep learning with symbolic regression to discover accurate, interpretable closed-form expressions from complex datasets efficiently.

Contribution

The paper introduces Ex-HiDeNN, a scalable, fast, and interpretable neural architecture that effectively derives closed-form expressions, outperforming traditional methods in benchmarks and engineering applications.

Findings

Ex-HiDeNN achieves significantly lower errors than traditional symbolic regression.

The method successfully discovers closed-form equations in engineering problems.

Ex-HiDeNN demonstrates high accuracy and efficiency on benchmark datasets.

Abstract

Data-driven science and computation have advanced immensely to construct complex functional relationships using trainable parameters. However, efficiently discovering interpretable and accurate closed-form expressions from complex dataset remains a challenge. The article presents a novel approach called Explainable Hierarchical Deep Learning Neural Networks or Ex-HiDeNN that uses an accurate, frugal, fast, separable, and scalable neural architecture with symbolic regression to discover closed-form expressions from limited observation. The article presents the two-step Ex-HiDeNN algorithm with a separability checker embedded in it. The accuracy and efficiency of Ex-HiDeNN are tested on several benchmark problems, including discerning a dynamical system from data, and the outcomes are reported. Ex-HiDeNN generally shows outstanding approximation capability in these benchmarks, producing orders of magnitude smaller errors compared to reference data and traditional symbolic regression. Later, Ex-HiDeNN is applied to three engineering applications: a) discovering a closed-form fatigue equation, b) identification of hardness from micro-indentation test data, and c) discovering the expression for the yield surface with data. In every case, Ex-HiDeNN outperformed the reference methods used in the literature. The proposed method is built upon the foundation and published works of the authors on Hierarchical Deep Learning Neural Network (HiDeNN) and Convolutional HiDeNN. The article also provides a clear idea about the current limitations and future extensions of Ex-HiDeNN.