University of Cambridge > > Microsoft Research Cambridge, public talks > Symbiotic design for machine intelligence systems

Symbiotic design for machine intelligence systems

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

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

Please be aware that this event may be recorded. Microsoft will own the copyright of any recording and reserves the right to distribute it as required.

This past year has seen a number of inspirational demos that illustrate the rapid development and increasing power of machine intelligence technologies. These new possibilities present a provocative challenge to researchers in human experience & design: how can machine intelligence be utilised in applications that augment people’s everyday experiences in meaningful ways. Medicine has been highlighted as one field that might particularly benefit from machine intelligence. In this talk, I will illustrate some of the research challenges that arise when getting machine intelligence working in a real-world setting. Drawing from the ASSESS MS project Рa system for tracking disease progression in multiple sclerosis patients using machine intelligence and perception, I will present three distinct examples: the design of a prototype to capture high quality data; the development of a tool to efficiently and consistently provide ground truth labels for the depth videos captured; and an iterative design process to develop visualisations that enable clinicians to integrate an algorithmic decision into their own clinical thinking. I close with the proposition of symbiotic design for intelligent systems: the machine learning algorithms at their core must shape as well as be shaped by the human activities they are designed to support.

This talk is part of the Microsoft Research Cambridge, public talks series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2022, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity