no code implementations • 31 Jul 2023 • Gabriela Barenboim, Luigi Del Debbio, Johannes Hirn, Veronica Sanz
We use Google's MusicVAE, a Variational Auto-Encoder with a 512-dimensional latent space to represent a few bars of music, and organize the latent dimensions according to their relevance in describing music.
no code implementations • 4 Oct 2022 • Miguel G. Folgado, Veronica Sanz, Johannes Hirn, Edgar G. Lorenzo, Javier F. Urchueguia
Traffic congestion is a major urban issue due to its adverse effects on health and the environment, so much so that reducing it has become a priority for urban decision-makers.
no code implementations • 10 Mar 2021 • Gabriela Barenboim, Johannes Hirn, Veronica Sanz
We explore whether Neural Networks (NNs) can {\it discover} the presence of symmetries as they learn to perform a task.