3.1MLJun 19
Orthogonal Discrepancy Kernels for Learning with Partial PhysicsSwapnil Manna, Timothy J. Rogers, Lawrence Bull
We introduce a semi-parametric framework for nonlinear system identification, which decouples discrepancy functions from physics-based components. Orthogonal Gaussian process regression balances sparse parameter selection (the white box) with discrepancy learning (the black box) to produce interpretable models from incomplete physics.