Dresden 2026 – wissenschaftliches Programm

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

AKPIK: Arbeitskreis Physik, moderne Informationstechnologie und Künstliche Intelligenz

AKPIK 2: Machine Learning Prediction and Optimization Tasks

Dienstag, 10. März 2026, 09:30–10:45, BEY/0127

	09:30	AKPIK 2.1	Bayesian Optimization for Mixed-Variable Problems in the Natural Sciences — •Yuhao Zhang, Ti John, Matthias Stosiek, and Patrick Rinke
	09:45	AKPIK 2.2	Overparametrization bends the landscape: BBP transitions at initialization in simple Neural Networks — •Brandon Livio Annesi, Chiara Cammarota, and Dario Bocchi
	10:00	AKPIK 2.3	Training convolutional neural networks with the forward - forward algorithm — •Matthias Schröter, Frauke Alves, and Riccardo Scodellaro
	10:15	AKPIK 2.4	Modeling resonant soliton interactions in the Kadomtsev-Petviashvili equation using PINNs — •Gerald Kämmerer
	10:30	AKPIK 2.5	Phase Transitions reveal Accuracy Hierarchies in Deep Learning — •Ibrahim Talha Ersoy, Andrés Fernando Cardozo Licha, and Karoline Wiesner