University of Cambridge > Talks.cam > Artificial Intelligence Research Group Talks (Computer Laboratory) > An Introduction to Federated Learning and its Applications in Medicine

An Introduction to Federated Learning and its Applications in Medicine

Add to your list(s) Download to your calendar using vCal

  • UserBlaise Thomson, Bitfount
  • ClockTuesday 30 November 2021, 13:15-14:15
  • HouseZoom.

If you have a question about this talk, please contact Mateja Jamnik.

Join us on Zoom

Machine learning and artificial intelligence continue to deliver groundbreaking advances in healthcare, promising to transform everything from diagnosis to drug discovery. However academic and clinical researchers alike are currently limited by a lack of access to the most relevant datasets for their research and ML model training, mostly due to legitimate privacy concerns. The resulting legal and technical obstacles usually prevent collaborations entirely, or at best incur months and years of complex legal and technical workarounds in order to enable data sharing.

Federated learning, in combination with other privacy-preserving ML techniques, is a leading candidate for eliminating this friction. It enables researchers to gather insights and train models on data which (a) remains held at all times by the organisation which owns it, and (b) never gets exposed in its raw form. It enables data owners to share the benefits of their data without giving up control or privacy. Bitfount is a powerful, easy-to-use platform for federated AI and data collaboration, designed to help researchers maximise the impact of their work. In this seminar, members of the Bitfount team will give a practical introduction to federated learning, its position in the array of privacy-preserving ML methods, how it can be combined with other techniques such as differential privacy, secure multi-party computation, homomorphic encryption and synthetic data, and how these techniques can be applied to solve real-world problems today both in academia and in industry.

BIO: Blaise Thomson is the founder and CEO of Bitfount and is a widely-recognised AI leader, researcher and successful entrepreneur. He was the founder and CEO of VocalIQ, which he sold to Apple in 2015, subsequently leading their Cambridge, UK engineering office and holding the role of Chief Architect for Siri Understanding. Blaise holds a PhD in Computer Science from the University of Cambridge, where he was also a Research Fellow, and is an Honorary Fellow at the Cambridge Judge Business School.

This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2021 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity