<ul><li>Artificial Neural Networks (ANNs) have achieved remarkable success, but suffer from limited generalization.</li><li>To overcome this limitation, a novel function approximator called Deep Sturm--Liouville (DSL) is introduced.</li><li>DSL enables continuous 1D regularization along field lines in the input space and integrates the Sturm--Liouville Theorem (SLT) into the deep learning framework.</li><li>DSL achieves competitive performance and improved sample efficiency on diverse multivariate datasets.</li></ul>

Deep Sturm--Liouville: From Sample-Based to 1D Regularization with Learnable Orthogonal Basis Functions

Discover more