Amin Jafarimoghaddam

(Department of Aerospace Engineering, Universidad Carlos III, Madrid, Spain)
hosted by Seminar Series on Scientific Computing

"From Residual Neural Networks to Neural ODEs – theory and applications"

This talk explores key developments in neural network architectures. The discussion begins with an examination of Residual Neural Networks and their relation to Neural Ordinary Differential Equations (Neural ODEs). We briefly review some of the advantages, and limitations of Neural ODEs. We also consider possible variations of Residual Neural Networks and their higher-order Neural ODE representation. Furthermore, we explore the possibility of networks equipped with average nonlinear programming techniques, which might be alternatives to addressing the deep learning issues. Finally, we highlight some potential practical applications.

Time:	Wednesday, 11.10.2023, 16:00
Place:	Hybrid (Room 32-349 and via Zoom)
Video:	https://uni-kl-de.zoom.us/j/63123116305?pwd=Yko3WU9ZblpGR3lGUkVTV1kzMCtUUT09

Termin als Datei downloaden und in den Kalender importieren.