Tipus de document
Treball de fi de grauData de publicació
Llicència de publicació
Si us plau utilitzeu sempre aquest identificador per citar o enllaçar aquest document: https://hdl.handle.net/2445/232178
Euler-Flow Activations in Neural ODEs
Títol de la revista
Autors
Director/Tutor
Contribució addicional
ISSN de la revista
Títol del volum
Resum
This thesis investigates whether using velocity fields derived from incompressible Euler equations as activation functions in residual neural networks offers advantages over using ReLUs for spatially structured classification tasks. The motivation for this study comes from two specific theoretical observations. Firstly, recent work has shown that approximating measure-preserving maps with ReLU perceptrons requires a large number of compositions that grows with the desired precision. Secondly, Arnold’s theorem identifies the geodesics of the group of volume-preserving diffeomorphisms as flows of the incompressible Euler equations. To test this hypothesis, three explicit families of solutions to the Euler equations in two dimensions are compared against ReLU and Siren on three two-dimensional classification tasks, with the number of parameters matched across all architectures. The results support the hypothesis for the main architecture tested: every non-ReLU activation outperforms ReLU by between ten and twenty-five percentage points across all tasks and seeds. However, further work is required to extend this result to deeper and more complex architectures.
Descripció
Treballs Finals de Grau de Matemàtiques, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2026, Director: Alejandro Haro i Domènec Ruiz-Balet
Recurs relacionat
Citació
Citació
GRÀVALOS TALLÓ, Bruna. Euler-Flow Activations in Neural ODEs. [consulted: 4 of November of 2026]. Available at: https://hdl.handle.net/2445/232178