Views provided by UsageCounts
handle: 2117/415271
Encontrar soluciones de EDPs reformulándolas en un problema de minimización es una tarea difícil debido a la presencia de un número infinito de mínimos locales y a la no convexidad genérica del funcional. En esta tesis de máster, utilizamos redes neuronales informadas por la física (PINNs) para encontrar nuevas soluciones no triviales a las ecuaciones de Euler incompresibles en dos dimensiones.
Trobar solucions d'EDPs reformulant-les en un problema de minimització és una tasca difícil a causa de la presència d'un nombre infinit de mínims locals i a la no convexitat genèrica del funcional. En aquesta tesi de màster, utilitzem xarxes neuronals informades per la física (PINNs) per trobar noves solucions no trivials a les equacions d'Euler incompressibles en dues dimensions.
Finding solutions to PDEs by recasting them into a minimization problem is a hard problem due to the presence of infinitely many local minima and generic non-convexity of the functional. In this master thesis we use physics informed neural networks (PINNs) to find new, nontrivial solutions to the incompressible two-dimensional Euler equations.
Àrees temàtiques de la UPC::Matemàtiques i estadística, machine learning, Fluid dynamics, Dinàmica de fluids, Machine learning, Aprenentatge automàtic, 2D euler equations, 500, Physics-informed neural networks, numerical methods for partial differential equations, 530, Classificació AMS::70 Mechanics of particles and systems::70K Nonlinear dynamics
Àrees temàtiques de la UPC::Matemàtiques i estadística, machine learning, Fluid dynamics, Dinàmica de fluids, Machine learning, Aprenentatge automàtic, 2D euler equations, 500, Physics-informed neural networks, numerical methods for partial differential equations, 530, Classificació AMS::70 Mechanics of particles and systems::70K Nonlinear dynamics
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
| views | 27 |

Views provided by UsageCounts