Rafael BischofinTowards Data Science4 Ideas for Physics-Informed Neural Networks that failedHere is a list of extensions for PINNs that either did not improve their performance, or broke them completely — so you do not have to try…Feb 11, 20232Feb 11, 20232
Rafael BischofinTowards Data Science10 Useful Hints and Tricks for Improving Physics-Informed Neural Networks (PINNs)A handful of tricks concerning the sampling, architecture, activation function, loss balancing, optimisers, data normalisation, and more.Feb 8, 20232Feb 8, 20232
Rafael BischofAI-Augmented Designing Process of a Pedestrian Bridge in SwitzerlandLeveraging AI to enhance designing processes in the AEC Industry: A Case Study of a Pedestrian Bridge in SwitzerlandFeb 6, 2023Feb 6, 2023
Rafael BischofinTowards Data ScienceMixture of Experts for PINNs (MoE-PINNs)Utilising Ensembles to enhance Physics-Informed Neural NetworksFeb 2, 20231Feb 2, 20231
Rafael BischofinTowards Data ScienceImproving Physics-Informed Neural Networks through Adaptive Loss BalancingHow to boost your PINN’s performance with ReLoBRaLo, Learning Rate Annealing and co.Jan 31, 20232Jan 31, 20232