The first day of the conference comprises a range of workshops, to be held on Tuesday 12th December. Delegates will find these events to be especially valuable where there is a current need to consider the introduction of new AI technologies into their own organisations.
There will be four half-day workshops. Delegates are free to choose any combination of sessions to attend. The programme of workshops is shown below. Note that the first session starts at 11 a.m. to reduce the need for delegates to stay in Cambridge on the previous night.
There is a lunch break from 12.30-13.15 and there are refreshment breaks from 14.45-15.15 and from 16.45-17.00.
Workshops organiser: Professor Adrian Hopgood, University of Portsmouth, UK
Sessions 1 and 2 - Stream 1 (11.00-12.30 and 13.15-14.45 Upper Hall)
Computational Scientific Discovery in Social Sciences
Dr Peter Lane, University of Hertfordshire, UK and Prof. Fernand Gobet, London School of Economics, UK
This workshop will explore some AI approaches to developing scientific models, particularly considering applications in social science. This area is relatively unexplored, and presents some unique challenges, particularly as models must address both the less-than-perfect accuracy of human behaviour as well as capture this behaviour in time-bound environments. We will provide an introduction and case-studies in this area and deliver a tutorial on GEMS, our own system of scientific discovery.
(*) GEMS - Genetically Evolving Models of Science - is a computational discovery system. Details of the project are at: https://gems-science.netlify.app (opens in new tab)
- Introduction to Computational Scientific Discovery in Social Sciences
- Tutorial of the GEMS(*) system, covering:
- setting up task definitions for scientific experiments
- defining a search space of candidate models
- searching techniques, such as Genetic Programming.
- visualisation and analysis of results
- Examples of applying this and related methodologies in Psychology and Social Sciences
Sessions 1 and 2 - Stream 2 (11.00-12.30 and 13.15-14.45 Peterhouse Lecture Theatre)
AI for Manufacturing and Supply Chains
Dr Giovanna Martinez-Arellano, University of Nottingham, UK
Since the Industrie 4.0 initiative was launched in Germany over more than a decade ago, the advancements on the Industrial Internet of Things and the developments in Cloud and Edge computing, there has been an accelerated advancement of research into the applications of AI across all levels of the manufacturing business, from the shopfloor to the supply chain. In this workshop, we will look at some of the most successful applications of AI in manufacturing and the supply chain as well the particular challenges this sector faces to achieve its scalability.
- Professor Alexandra Brintrup, University of Cambridge, is Professor in Digital Manufacturing and is leading the Supply Chain Artificial Intelligence Lab. Her talk will be on various applications of data analytics and machine learning for the development of automated and scalable optimisation and distributed decision making technologies for Supply Chain Management and Logistics.
- Dr Sebastian Pattinson, Associate Professor at University of Cambridge, is developing learning manufacturing systems and 3D printed medical devices. His talk will be a dive into the use of AI approaches to improve the control of the 3D printing process.
- Mr Athanasios Papas is postgraduate researcher in Metrology at the University of Nottingham. He will present on Artificial intelligence methods for smarter data processing. As the need for the manufacturing of complex surfaces rises, an increased demand is placed on metrology as a means of quality control. However, the process of data acquisition and analysis has reached a bottleneck. The introduction of virtual instruments allows for smarter data processing methods, improving the speed and accuracy of measurements. As part of this workshop, an overview will be given on how artificial intelligence can improve the performance of different metrological applications for a specific task, with focus on surface and form metrology.
- Dr Giovanna Martinez Arellano is Senior Research Fellow in Industrial AI at the University of Nottingham. Her talk will be around Omnifactory, the new national demonstrator of flexible and reconfigurable manufacturing systems and the applications of AI to support such flexibility.
Sessions 3 and 4 - Stream 1 (15.15-16.45 and 17.00-18.30 Upper Hall)
AI Challenges in Healthcare
Dr Kieran Zucker, University of Leeds, UK and Professor Jeremy Wyatt, University of Southampton, UK
Despite the excited media coverage around artificial intelligence, particularly in the healthcare setting, there are many challenges that receive little attention despite their importance. In this session we aim focus on some of these crucial but less spoken-about issues. You will hear from academic and industry experts who will discuss, amongst other topics:
The speakers will include:
- healthcare AI in developing countries
- commercial and NHS collaboration for AI development
- communicating healthcare AI to patients and the public
- the use of federation for privacy preserving international algorithm development
- the issues that arise from open-source development
- Dr Stelios Theophanous (Leeds Teaching Hospitals NHS Trust)
- Dr Joshua Au Yeung (Kings College Hospital NHS Trust)
- Dr Mark Bailey (Bristol Royal Infirmary)
- Mr Will Browne (Carnall Farrar)
- Dr Janak Gunatilleke (KPMG)
Sessions 3 and 4 - Stream 2 (15.15-16.45 and 17.00-18.30 Peterhouse Lecture Theatre)
Professor Carl Adams, Cosmopolitan University Abuja, Nigeria / Mobi Publishing, Chichester, UK and Dr Anita Khadka, North Eastern University, London, UK
This workshop will explore challenges of testing AI, particularly adaptive systems and and those used in safety critical environments. The workshop will present insights from a project developing AI testing approaches and tools and will be demonstrated using case examples. The workshop will be engaging, encouraging participation and sharing of insights around this increasingly important aspect of AI based systems. The toolsets and approaches covered include affordances mapping (AM), bounds of applicability (BoA), and temporal modelling (TM), which can be applicable to other AI systems. The workshop also engages participants in practical applications around a further case example.
- Part one: Challenges
- Challenges of testing systems and software
- Challenges of AI testing
- Insights from software testing; safety critical systems testing
- Part two: Insights from AI testing research project
- Generic approaches to testing AI
- Affordances mapping (AM), bounds of applicability (BoA), and temporal modelling (TM) approaches
- Six brief case examples; an in-depth case study
- tea break
- Part three: Application to case example
This element of the workshop will be focussed around applying AM, BoA and TM around a case study. It will also explore other approaches to testing AI for the case study example.
The presenters will be:
- Professor Carl Adams (Cosmopolitan University Abuja / Mobi Publishing)
- Dr Anita Khadka (North Eastern University, London)
- Dr Yuchen Zhao (University of York)
- Dr Andrew M'manga (Bournemouth University)
- Dr Heather Shaw (Lancaster University)
- Mohsen Eslamnejad (University of Portsmouth)