no code implementations • 1 Oct 2023 • Rafael Bischof, Florian Scheidegger, Michael A. Kraus, A. Cristiano I. Malossi
Neural Image Classifiers are effective but inherently hard to interpret and susceptible to adversarial attacks.
no code implementations • 29 Nov 2022 • Vera M. Balmer, Sophia V. Kuhn, Rafael Bischof, Luis Salamanca, Walter Kaufmann, Fernando Perez-Cruz, Michael A. Kraus
For conceptual design, engineers rely on conventional iterative (often manual) techniques.
2 code implementations • 19 Oct 2021 • Rafael Bischof, Michael Kraus
Physics-Informed Neural Networks (PINN) are algorithms from deep learning leveraging physical laws by including partial differential equations together with a respective set of boundary and initial conditions as penalty terms into their loss function.