| 03-07-2023 |
Redes Neuronales para encajes de moleculas
Modelos de Deep Learning basado en grafos han recien superado a otros metodos clasicos en quimica computacional para la busqueda de moleculas con propiedades especificas, por ejemplo farmacos y catalizadores de bioprocesos. El objetivo de la IPRE es desarrollar redes neuronales sobre grafos, para calcular la forma de encaje optimo de pares de moleculas desde un database. Se necesita no partir desde cero con redes neuronales para poder avanzar sin problemas, y es util si se tiene una pasion para problemas dificiles con aspectos combinatorios y geometricos.
Keywords:
Tiene un método de evaluación Nota 1-7, con 10 créditos y tiene 2/2 vacantes disponibles |
Mentor(es): Ver en la plataforma |
| 06-01-2022 |
Liquid Democracy: Modelling, Analysis, and Computational Implementation
Liquid democracy is a new paradigm of democratic decision-making, based on the idea that voters can delegate their votes transitively to people they consider most qualified for the particular election that is being held. The study of liquid democracy from an algorithmic and computational point of view, which is a branch of the area of "computational social choice", has recently started through a couple of very influential articles; for example, https://ojs.aaai.org/index.php/AAAI/article/view/11468. Despite how interesting these works are, we believe that they have not yet managed to capture all the complexities that these types of dynamics have in reality. The idea is to develop extensions of this model that better fit the requirements of current political science, and from that to analyze its mathematical and computational properties. The work will be interdisciplinary with components of mathematics, computing, and political science.
Prerequisites:
IIC1253
Evaluation method: Nota 1-7, with 0/1 available vacants |
Mentor(s): Open in the plataform |
| 03-07-2023 |
Keywords:
Evaluation method: Nota 1-7, with 2/2 available vacants |
Mentor(s): Open in the plataform |