AI RESEARCH
A Novel Tensor Product-Based Neural Network for Solving Partial Differential Equations
arXiv CS.LG
•
ArXi:2605.29688v1 Announce Type: new This paper presents the Tensor Product Network (TPNet), a novel neural architecture for efficient and accurate function approximation and PDE solving. The core of the proposal involves constructing the solution explicitly as a linear combination of basis functions integrated into the network, with coefficients determined by a direct least-squares solve, thereby bypassing traditional gradient-based