2 papers
cs.CV2026
Training Deep Visual Networks Beyond Loss and Accuracy Through a Dynamical Systems Approach
Hai La Quang, Hassan Ugail, Newton Howard +3
Deep visual recognition models are usually trained and evaluated using metrics such as loss and accuracy. While these measures show whether a model is improving, they reveal very l…
math.DS2023
The R-IFSs and their attractors
Hung Nguyen Viet, Duy Mai The, Thanh Vu Thi Hong
This paper introduces a new class of iterated function systems (IFSs) called R-IFSs, which include both rotation/reflection maps and contraction maps. The study of R-IFSs is motiva…