We are living in an increasingly complex ecosystem of behavioural profiling and personal data analytics. In this talk, I present our ongoing work on utilising edge-computing to improve the scalability and privacy of user-centred analytics in the context of personal data. I present an ecosystem where devices and resources centred around the user, collectively referred to as the edge, can complement the cloud for providing privacy-aware, yet accurate and efficient analytics. I then present the evaluations of the proposed framework for applying privacy-preserving deep learning techniques on a number of exemplar applications, and discuss the broader implications of such approaches for future systems such as the Databox platform.
The hashtag to use for tweeting about this event is #oiicolloquia
Data Dump to delete
- Name: Dr Hamed Haddadi
- Affiliation: The Faculty of Engineering, Imperial College London.
- URL: https://www.imperial.ac.uk/people/h.haddadi
Dr Hamed Haddadi is a Senior Lecturer (~Associate Professor) and the Deputy Director of Research in the Dyson School of Design Engineering, at The Faculty of Engineering at Imperial College London. He leads the Systems and Algorithms Design Laboratory (SysAl). He is also an Academic Fellow of the Data Science Institute.
His research interest are in User-Centered Systems, IoT, Applied Machine Learning, Privacy, and Human-Data Interaction.