by Research Team | Dec 29, 2018 | Research Publications
Author(s): Kneidinger-Müller, Bernadette Abstract: Digital traces occur as a consequence of using digital devices or applications, but they can also be produced intentionally, as in the case of self-tracking activities. Self-tracking increases the amount of data that...
by Research Team | Dec 17, 2018 | Research Publications
Author: Higham, Catherine F. Higham, Desmond J. Abstract: Multilayered artificial neural networks are becoming a pervasive tool in a host of application fields. At the heart of this deep learning revolution are familiar concepts from applied and computational...
by Research Team | Nov 6, 2018 | Research Publications
Author(s): Urteaga, IñigoMcKillop, MollieLipsky-Gorman, SharonElhadad, Noémie Abstract: We investigate the use of self-tracking data and unsupervised mixed-membership models to phenotype endometriosis. Endometriosis is a systemic, chronic condition of women in...
by Research Team | Nov 6, 2018 | Research Publications
Author(s): Miolane, NinaMathe, JohanDonnat, ClaireJorda, MikaelPennec, Xavier Abstract: We introduce geomstats, a python package that performs computations on manifolds such as hyperspheres, hyperbolic spaces, spaces of symmetric positive definite matrices and Lie...
by Research Team | Oct 25, 2018 | Research Publications
Author(s): MacKay, MatthewVicol, PaulBa, JimmyGrosse, Roger Abstract: Recurrent neural networks (RNNs) provide state-of-the-art performance in processing sequential data but are memory intensive to train, limiting the flexibility of RNN models which can be trained....