Opening the Black-Box: Symbolic Regression with Kolmogorov-Arnold Networks for Energy Applications
This work addresses the need for interpretable and explainable models in high-stakes domains like nuclear power, though it is incremental as it builds on existing KAN methods applied to new data.
The paper tackled the problem of interpretability in machine learning for sensitive industries by comparing Kolmogorov-Arnold Networks (KANs) to feedforward neural networks (FNNs) on nuclear power datasets, finding that KANs achieve comparable accuracy while transforming into symbolic equations for perfect interpretability and learning physical relations from data.
While most modern machine learning methods offer speed and accuracy, few promise interpretability or explainability -- two key features necessary for highly sensitive industries, like medicine, finance, and engineering. Using eight datasets representative of one especially sensitive industry, nuclear power, this work compares a traditional feedforward neural network (FNN) to a Kolmogorov-Arnold Network (KAN). We consider not only model performance and accuracy, but also interpretability through model architecture and explainability through a post-hoc SHAP analysis. In terms of accuracy, we find KANs and FNNs comparable across all datasets, when output dimensionality is limited. KANs, which transform into symbolic equations after training, yield perfectly interpretable models while FNNs remain black-boxes. Finally, using the post-hoc explainability results from Kernel SHAP, we find that KANs learn real, physical relations from experimental data, while FNNs simply produce statistically accurate results. Overall, this analysis finds KANs a promising alternative to traditional machine learning methods, particularly in applications requiring both accuracy and comprehensibility.