<ul><li>Neural networks have emerged as powerful tools for modeling complex physical systems.</li><li>A novel architecture, called Hybrid Parallel Kolmogorov-Arnold Network (KAN) and Multi-Layer Perceptron (MLP) Physics-Informed Neural Network (HPKM-PINN) has been proposed.</li><li>HPKM-PINN combines the strengths of KAN's interpretable function approximation and MLP's nonlinear feature learning for enhanced predictive performance.</li><li>Benchmark experiments show that HPKM-PINN significantly reduces loss values compared to standalone KAN or MLP models in solving partial differential equations (PDEs).</li></ul>

Enhancing Physics-Informed Neural Networks with a Hybrid Parallel Kolmogorov-Arnold and MLP Architecture

Discover more