Seminar details

Zoom link

3 March 2022 - 14h30
Machine Learning Safety
by Xiaowei Huang from University of Liverpool

Abstract: Machine learning has been proven practical in solving complex problems that cannot be solved before, but was also found to be not without any shortfall. This talk will address the safety and security risks of applying machine learning to safety critical systems. We will provide an overview of the known risks in the machine learning development cycle, discussing a number of properties such as generalisation, uncertainty, robustness, poisoning, backdoor, and some privacy-related properties. Based on the properties, we will discuss the existing methods, including verification and validation methods, that have been intensively developed in the past years to work with some of these properties. Future research directions will also be discussed.

Participer à la réunion Zoom

ID de réunion : 960 3017 8756
Code secret : 933895
Une seule touche sur l’appareil mobile
+33186995831,,96030178756# France
+33170372246,,96030178756# France

Composez un numéro en fonction de votre emplacement
+33 1 8699 5831 France
+33 1 7037 2246 France
+33 1 7037 9729 France
+33 1 7095 0103 France
+33 1 7095 0350 France
ID de réunion : 960 3017 8756
Trouvez votre numéro local :

Participer à l’aide d’un protocole SIP

Participer à l’aide d’un protocole H.323 (États-Unis (Ouest)) (États-Unis (Est)) (Amsterdam Pays-Bas) (Allemagne)
Code secret : 933895
ID de réunion : 960 3017 8756

Contact | Site Map | Site powered by SPIP 3.2.15 + AHUNTSIC [CC License]

info visites 1862788