Presenter: Alessandro EpastoMonday, September 18th, 2023 11:30Location: Sala Ciminiera, 5th floor Corso Castelfidardo 34 ABSTRACT Clustering is a fundamental unsupervised machine learning problem that lies at the core of several real-world applications. While traditional clustering algorithms have not considered the privacy of the users providing the data, recently private clustering […]
Seminars
Presenter: Federico CeruttiWednesday, June 21st, 2023 11:00Location: Sala Maxwell, 5th floor Corso Castelfidardo 34 ABSTRACT When collaborating with an AI system, we must assess when to trust its recommendations. Suppose we mistakenly trust it in regions where it is likely to err. In that case, catastrophic failures may occur, hence […]
Presenter: Anna Maria MandalariWednesday, July 5th, 2022 11:00Location: SmartData@Covivio We are seeing an increasing abundance of potentially intrusive and privacy-invasive IoT devices in our lives, from smart city projects to the connected home. In this talk, I will explore my longer-term research vision toward building an IoT user-centred ecosystem which […]
Presenter: Marco CaniniTuesday, April 26th, 2022 14:00Location: Sala Ciminiera, 5th floor Corso Castelfidardo 34 ABSTRACT Scaling deep learning to a large cluster of workers is challenging due to high communication overheads that data-parallelism entails. This talk describes our efforts to rein in distributed deep learning’s communication bottlenecks. We describe SwitchML, […]
Presenter: Olivia CaramelloThursday, May 27th, 2021 18:00Location: Microsoft Teams – click here to join Get ticket on Eventbrite ABSTRACT I will introduce the theory of toposes as unifying ‘bridges’, give a survey of the main results obtained so far and discuss some work in progress and future research directions on […]
The PIMCity European project has organized the workshop “Be Aware! Keep Calm and read your privacy policies”, which will take place (virtually) on 25th November 2020 at 16:00 CEST. The workshop aims to provide customers and entities whose activities involve the processing of personal data with key elements of privacy […]
Presenter: Vittorio Di TomasoThursday, Feb 13th, 2020 16:30Location: Maxwell Room DET- Corso Castelfidardo, 39, Torino Get ticket on Eventbrite ABSTRACT Natural language processing (NLP) is a crucial part of artificial intelligence and one of the most important technologies of the information age. Applications of NLP are everywhere, because people communicate […]
Presenter: Mattia ZanellaWednesday, November 6th, 2019 14:30Location: Aula Seminari DISMA – Corso Duca degli Abruzzi 24, Torino Get ticket on Eventbrite ABSTRACT In this seminar, we concentrate on the traffic flow description with uncertain interaction forces. We explain the typical scattering of the fundamental diagram in terms of the macroscopic […]
Presenter: Daniel Dubois (Northeastern University)Friday, October 25th, 2019 15:30Location: Maxwell Room 5th Floor DET – Corso Castelfidardo, 42/a Get ticket on Eventbrite ABSTRACT The “Data Revolution” is transforming our society in an irreversible way at a pace Internet of Things (IoT) devices are increasingly found in everyday homes, providing useful functionality for devices such […]
Presenter: Hanan Samet (University of Maryland) Tuesday, May 28th, 2019 11:30 Location: Maxwell Room 5th Floor DET – Corso Castelfidardo, 42/a Get ticket on Eventbrite Abstract An introduction is given to the spatial database issues involved in the design of geographic information systems (GIS) from the perspective of a computer scientist. […]
Presenter: Emilio Paolucci (Politecnico di Torino) Friday, May 31st, 2019 15:00 Location: Maxwell Room 5th Floor DET – Corso Castelfidardo, 42/a Get ticket on Eventbrite Abstract Today, digitization and big data analytics penetrate all areas of life and create new ways of working, communicating and cooperating. Connecting individuals, enterprises, devices […]
Presenter: Patrizio Frosini Wednesday, May 15th, 2019 14:35 Location: Room 7D – Corso Duca degli Abruzzi, 24 Get ticket on Eventbrite Abstract In this talk we illustrate a new mathematical model for machine learning, which follows from the assumption that data cannot be studied directly, but only through the action […]