Miguel Lazaro Gredilla

Miguel previously earned his PhD in machine learning at Universidad Carlos III de Madrid. In his thesis, Miguel developed a sparse Gaussian process model which has become the de facto benchmark for fast regression algorithms. Follow-up work includes co-proposing the re-parameterization trick for VAEs.

Since then, Miguel has been working on brain-inspired knowledge representation, inference, and learning: CAPTCHA breaking, cognitive maps representation, cognitive programming, etc. He has been a visiting scholar at the University of Cambridge and the University of Manchester, and has been published in Science, NIPS, ICML, JMLR, and several IEEE journals.