<ul><li>Symbolic regression (SR) aims to discover closed-form mathematical expressions that accurately describe data, offering interpretability and analytical insight beyond black-box models.</li><li>Introducing LIES (Logarithm, Identity, Exponential, Sine), a fixed neural network architecture with interpretable primitive activations optimized to model symbolic expressions.</li><li>The framework extracts compact formulae from LIES networks by training with oversampling strategy and a tailored loss function to promote sparsity and prevent gradient instability.</li><li>Experiments on SR benchmarks show that the LIES framework consistently produces sparse and accurate symbolic formulae outperforming all baselines, with the importance of each design component demonstrated through ablation studies.</li></ul>

Sparse Interpretable Deep Learning with LIES Networks for Symbolic Regression

Discover more