Výsledky vyhledávání - "Bischof, Rafael"

Report

Counterfactual Image Generation for adversarially robust and interpretable Classifiers

Autor: Bischof, Rafael, Scheidegger, Florian, Kraus, Michael A., Malossi, A. Cristiano I.

Neural Image Classifiers are effective but inherently hard to interpret and susceptible to adversarial attacks. Solutions to both problems exist, among others, in the form of counterfactual examples generation to enhance explainability or adversarial

Externí odkaz: http://arxiv.org/abs/2310.00761

Zobrazit plný text záznamu

Report

Design Space Exploration and Explanation via Conditional Variational Autoencoders in Meta-model-based Conceptual Design of Pedestrian Bridges

Autor: Balmer, Vera M., Kuhn, Sophia V., Bischof, Rafael, Salamanca, Luis, Kaufmann, Walter, Perez-Cruz, Fernando, Kraus, Michael A.

Publikováno v: Automation in Construction Volume 163, July 2024, 105411

For conceptual design, engineers rely on conventional iterative (often manual) techniques. Emerging parametric models facilitate design space exploration based on quantifiable performance metrics, yet remain time-consuming and computationally expensi

Externí odkaz: http://arxiv.org/abs/2211.16406

Zobrazit plný text záznamu

Report

Multi-Objective Loss Balancing for Physics-Informed Deep Learning

Autor: Bischof, Rafael, Kraus, Michael

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

Externí odkaz: http://arxiv.org/abs/2110.09813

Zobrazit plný text záznamu