As part of the UDRC phase III, our second themed meeting on Deep Learning and Machine Learning will be held on Thursday 14^th November 2019, at Queen’s University Belfast. This event is intended for academic researchers, industrial partners and Dstl staff to learn about and discuss current trends in deep learning. The program will consists of a series of talks covering modern machine learning and its applications to current defence/security problems followed by a networking session. We will also present a Dstl Challenge competition. We also invite industry to give short pitches on the problems they face in this area.

9:00 Refreshments

9:15 Welcome and introduction to the day, Neil Robertson, Queen’s University Belfast

9:25 Semantic information pursuit in multi-modal data: MURI project report, John Shawe-Taylor, University College London

10:10 Industrial Use Case and Lessons Learned, Chris Dickson, Thales

10:40 Refreshments

11:00 Multi-label Classification: A Deep Sparse Decomposition Perspective, Mehrdad Yaghoobi, University of Edinburgh

11:20 Robust Generative NNs, Nikolaos Dionelis, University of Edinburgh

11:40 Deep Learning with Guarantees, Henry Gouk, University of Edinburgh

12:00 Single Image Super-Resolution via CNN Architectures and TV-TV Minimization, Joao Mota, Heriot-Watt University

12:20 Multi-modal Fusion, Shiyang Yan, Queen’s University Belfast

12:40 Lunch

13:25 Open industry problems - 5 minute pitches

13:55 Dstl Challenge

14:55 Refreshments

15:15 Dstl: AI Building Blocks for Defence and Security

15:45 Plenary discussion (industry, Dstl and academia) - debate role of ML in defence

16:30 Close

Places are limited at this even therrefore if you would like to come along then please RSVP to janet.forbes@ed.ac.uk