2 papers
cs.LG2026
A derivative-fidelity failure mode in physics-informed neural networks: strengthened benchmark evidence from function-value training
Koji Koyamada
Physics-informed neural networks (PINNs) use automatic differentiation to impose differential-equation residuals, but good agreement in function values does not necessarily imply a…
cs.CV2020
Learning of Art Style Using AI and Its Evaluation Based on Psychological Experiments
Mai Cong Hung, Ryohei Nakatsu, Naoko Tosa +2
GANs (Generative adversarial networks) is a new AI technology that can perform deep learning with less training data and has the capability of achieving transformation between two…