GOL will participate to the virtual open day of the Engineering School of Università degli Studi di Firenze Connect February 18th, 2021, at 17:00 CET at https://meet.google.com/jaq-hkkd-ugs Info: Virtual meeting: an introduction to the research activities at the Global Optimization
Possible research topics in ML: – Keyword spotting. – Spoken language detection
K-means is one out of a bunch of widely used clustering techniques. In this thesis, we plan to experiment with global optimization algorithms which use K-means as a local optimization solver Assigned: September 2019, Candidate: Pierluigi Mansueto Expected completion:
This thesis is devoted to the re-implementation of a very large scale kernel ridge regression software tool and to its extension to the semi-supervised case Started: November 2018 Candidate: Enrico Civitelli Graduated: April 2019
Managing inventories when the demand is uncertain is a challenging problem involving forecasting, modeling and optimization. This thesis is devoted to the extension of classical models, like the newsvendor, to multiple products, integer order quantities, logical constraints, assortment, and other
Analytics has found its place in most sports. This thesis is devoted to analyze some publicly available tennis data and try to extract significant information by means of machine learning. (image credits: https://www.ubitennis.com/blog/2015/04/22/tennis-e-statistiche-avanzate-le-cause-di-un-rapporto-difficile/)
We would like to experiments with optimization methods applied to DNN’s in order to obtain a sparse trained network, i.e. a network with a small number of neurons or connections.
This thesis is devoted to experiment numerical optimization techniques on the D-Wave quantum computer We will simulate some combinatorial optimization problems and try to find innovative problem mapping in order to fully exploit the capacity of the quantum annealing machine.
How to use information collected during past matches in order to be able to predict the final result of a match? This thesis explores machine learning methods and features extraction towards the goal of being able to anticipate the final result.
Despite the progress of medicine in recent decades, epilepsy is a disease whose knowledge is still limited. About one third of patients with this disease continue to present crises despite pharmacological treatments, surgical interventions, and the medical assistance. The most