2 papers
cs.LG2025
ChemKANs for Combustion Chemistry Modeling and Acceleration
Benjamin C. Koenig, Suyong Kim, Sili Deng
Efficient chemical kinetic model inference and application in combustion are challenging due to large ODE systems and widely separated time scales. Machine learning techniques have…
cs.LG2025
LeanKAN: A Parameter-Lean Kolmogorov-Arnold Network Layer with Improved Memory Efficiency and Convergence Behavior
Benjamin C. Koenig, Suyong Kim, Sili Deng
The recently proposed Kolmogorov-Arnold network (KAN) is a promising alternative to multi-layer perceptrons (MLPs) for data-driven modeling. While original KAN layers were only cap…