Throughout 2021, Manchester's Turing Fellows have been presenting their Turing-funded research.
In the final of Manchester's presentations, Mark Elliot will present his research with project co-lead Adriane Chapman at the University of Southampton.
In partnership with The Alan Turing Institute, the University of Southampton invites you to watch Turing Fellows Jacek Brodzki, Adriane Chapman, Mark Elliot (University of Manchester), and Pamela Ugwudike present the research and findings of their Pilot Projects.
14:00-14:05 - Introduction by Peter Smith, Turing University Lead
14:05-14:30 - Presentation by Pamela Ugwudike and Age Chapman:
A multidisciplinary study of predictive artificial intelligence technologies in the criminal justice system.
The project explored a classic predictive policing algorithm to investigate conduits of bias. Whilst many studies on real data have shown that predictive policing algorithms can create biased feedback loops, few studies have systematically explored whether this is the result of legacy data, or the algorithmic model itself. To advance the empirical literature, this project designed a framework for testing predictive models for biases. With the framework, the project created and tested: (1) a computational model that replicates the published version of a predictive policing algorithm, and (2) statistically representative, biased and unbiased synthetic crime datasets, which were used to run large-scale tests of the computational model. The study found evidence of self-reinforcing properties.
14:30-14:55 - Presentation by Jacek Brodzki: Topological and neural networks generalisations:
Neural networks are at the centre of many remarkable applications of AI. These powerful classification tools are great when they work well, but have demonstrated weaknesses where they fail at surprisingly easy tasks. This talk will summarise the results of our pilot project devoted to the study of the geometry of the decision boundaries of neural networks as a predictor for their performance.
14:55-15:20 - Presentation by Adriane Chapman and Mark Elliot: Anonymisation and Provenance: Expression data environments with PROV.
The Anonymisation Decision-Making Framework (ADF) is a comprehensive practice designed for assessing and controlling the risks of sharing and disseminating data. This project examines how to use provenance to support anonymization decision-making. To enable this, we analyze the mapping of concepts between ADF and prov. We have operationalized provenance into the framework, and analyse the suitability via real use cases. We have created prototype tool support from simulators to reasoners.
15:20-15:30 - Closing remarks with Peter Smith