Page 1 of 11 to 88 of 88 Past Events
2025
December
November
-
AI-Driven Synthetic Whole Slide Imaging and Cellular Biomarker Quantification for Computational Pathology
-Computational pathology represents a transformative paradigm in precision medicine, leveraging artificial intelligence to enhance diagnostic accuracy and streamline clinical workflows. This presentation showcases a comprehensive research portfolio addressing critical challenges across multiple pathological domains through advanced AI methodologies. Our work encompasses progressive context encoders for anomaly detection (P-CEAD) on whole...
-
AI-Driven Synthetic Whole Slide Imaging and Cellular Biomarker Quantification for Computational Pathology
-Computational pathology represents a transformative paradigm in precision medicine, leveraging artificial intelligence to enhance diagnostic accuracy and streamline clinical workflows. This presentation showcases a comprehensive research portfolio addressing critical challenges across multiple pathological domains through advanced AI methodologies. Our work encompasses progressive context encoders for anomaly detection (P-CEAD) on whole...
October
-
Cyber Security in Cyber-Physical Systems: A Journey
-Cyberphysical Systems (CPS) are transforming the way we interact with the physical world around us. However, CPS systems present unique challenges due to the complexity, constraints, and dynamic nature of the interactions. Cyber security is a major concern in CPS systems, particularly due to the large amount of sensitive data...
-
Towards LLM-powered social assistants
-Research in multi-agent systems has a long history of borrowing social concepts from human society and developing computational counterparts, with the aim of promoting orderly social interactions in societies of autonomous agents. As human communication and coordination becomes increasingly mediated by software, this raises the question of whether we can...
June
-
GRASP - Generative ReAsoning beyond Scaling uP
-Processing and generating language in ways that align with human expectations—both in communication and reasoning—requires computational representations that approximate how humans understand, abstract, and manipulate knowledge. Generative Large Language Models (LLMs), powered by vast data and extensive parameters, have achieved impressive alignment with human-like outputs. Though not explicitly trained for...
-
Advancing Predictive Runtime Verification through Multi-Model Approaches and Process Mining
-This talk explores the integration of Predictive Runtime Verification (PRV) and Process Mining techniques to enhance the reliability and efficiency of autonomous systems. We begin by presenting a multi-model PRV approach that addresses the complexity of systems composed of multiple components. This method improves traditional PRV by utilizing individual component...
May
-
Many Minds are Better Than One: Towards a Dialogical Turn in Logic
-Both the ancient Greek and Indian traditions primarily conceived of logic as an inherently dialogical process. However, it is the Enlightenment conception of logic as providing prescriptive guidance for individual agent reasoning that has come to dominate research into logics for AI. In this talk I will argue for a renewal...
-
Multimodal Scientific Content Generation with LLMs
-Generating scientific images (e.g., scientific figures) by hand can often be a time-consuming laborious task, where some popular coding languages such as TikZ come with a steep learning curve. Automatizing this process promises to facilitate and accelerate scientific multimodal content production. In this talk, I will discuss our recent approaches...
April
March
February
2024
November
July
-
Towards understanding 3D poses and gestures of multiple hands
-Hands are primary interacting tools that provide humans an ability to interact with their outer environments. Therefore, recognizing poses and actions (gestures) of hands from images and videos is essential to comprehensively understand the daily human intentions. Challenges occur when more than one hand appear in an image, due to...
-
A journey of the adoption of Blockchain in IoT Environments: Opportunities and Challenges
-Blockchain technology has emerged as a solution for providing transparency and trusted information in a decentralized and resilient manner. Particularly, there are significant potential benefits in integrating blockchain technology with the Internet of Things (IoT). However, adopting blockchain in hardware-constrained environments presents challenges. This integration introduces new issues, especially in...
May
April
-
Safety in conversational AI: Meaning is massively influenced by context
-While the NLP community has traditionally explored the ethical issues of text-based models (such as hate speech detection, inherent biases of the system etc), real-world conversations and dialogues differ significantly from structured, written text documents, and this brings with it its own unique set of safety challenges. From an understanding...
-
Multi-Agent Equilibria: From Verification to Modification and Beyond
-The classical notion of correctness in formal verification is not appropriate for multi-agent systems–-it does not capture the strategic behaviour of rational agents. As such, a different notion of correctness was proposed through the concept of rational verification. In doing so, we transform multi-agent systems into multi-player games and use...
March
-
Exploring TransNational Education (TNE) with Aberdeen Institute as a case study
-For decades, TNE existed in one form or another with USA often leading the field in innovative and accessible education aligned to the home-country educational standards but provided locally. In recent years, this form of education has been recognised by many countries as strategic framework to collaborate in developing necessary...
-
"A Day in the Life" of a digital forensics investigator
-Craig Porter from the OpenText company will present a talk about “A Day in the Life” of a digital forensics investigator. Delving into the captivating world of digital investigations, Porter will shed light on the methodologies, challenges, and pivotal role of a digital forensics investigator. Moreover, Craig will showcase their...
-
On the Practices for Evaluating Generative AI
-Recent years have seen remarkable advancements in Generative AI, ranging from text-to-text models like ChatGPT, to text-to-image models like DALLE3, and most recently, text-to-video models like Sora. With groundbreaking innovations in unsupervised learning and scalable architectures, these generative models demonstrate wide-ranging capabilities in understanding textual instructions and producing responses in...
2023
December
November
-
Critical Infrastructure Protection: Current Challenges and Solutions
-Join us for an informative seminar with Prof. Leandros Maglaras, one of the world's top cybersecurity experts, as he delves into the evolving challenges and solutions surrounding the protection of our critical digital infrastructures.
-
Expressive Automated Planning via Satisfiability Modulo Theories
-Planning is a fundamental activity, impacting our daily lives in many and varied ways. The planning task consists of selecting a sequence of actions to achieve a specified goal from specified starting conditions. This type of problem arises frequently in many contexts. Consider, for example, holiday planning. Various interleaved elements...
-
Wearable Activity Trackers and Privacy: Assessment of the Risks, Threats, and Countermeasures
-Join us for an enlightening session with Dr. Noé Zufferey, postdoctoral fellow at the University of Lausanne as he delves into the privacy threats related to the use of wearable activity trackers.
-
Uncovering Implicit Inferences for Improved Relational Argument Mining
-Argument mining seeks to extract arguments and their structure from unstructured texts. Identifying relations between arguments (such as attack, support, and neutral) is a challenging task because two arguments may be related to each other via implicit inferences. This task often requires external commonsense knowledge to discover how one argument...
-
CyberForce: A Federated Reinforcement Learning Framework for Malware Mitigation
-Join Chao Feng from the University of Zurich as he unveils the CyberForce framework, a novel approach in malware mitigation for IoT devices using federated reinforcement learning.
-
HW/SW Co-design for Security Systems
-Tune in to our online seminar with Huimin Li from Delft University of Technology, Netherlands. Unpack the details of HW/SW co-design and its impact on constructing resilient security architectures. Understand how intertwining hardware and software methodologies can result in enhanced and secure electronic solutions.
-
Towards a Robust, Effective, and Resource-Efficient Machine Learning Technique for IoT Security Monitoring
-Join us for a seminar by Dr. Idris Zakariyya, a renowned cybersecurity professional, as he delves into the challenges and solutions for employing Deep Neural Networks in IoT security monitoring.
October
-
It's more than just money: The real-world harms from ransomware attacks
-Join Nandita Pattnaik in a comprehensive exploration of the aftermath of ransomware attacks, revealing the intricate spectrum of damages that span beyond monetary losses.
-
Beyond Bytes and Bugs: Navigating the Human Side of Cybersecurity
-Join cybersecurity veteran Paul Baird as he delves beyond technicalities to unravel the humanistic aspects of cybersecurity, emphasizing the often-overlooked non-technical attributes crucial for success in the industry.
-
A First Look at Digital Rights Management Systems for Secure Mobile Content Delivery
-Join Amir Rafi as he delves into the intricate world of Digital Rights Management (DRM) systems on mobile platforms, offering a comprehensive security assessment of major DRM technologies in the era of cloud-based content delivery.
-
High-Profile Data Breach: An In-Depth Analysis of Crypto-Wallet Case.
-Join us for an enlightening session with Assistant Professor Svetlana Abramova as she delves into the repercussions of a data breach on crypto-wallet users. Discover key findings, challenges, and valuable lessons from this real-life incident.
July
March
-
Towards Closed-Loop Interactive Autonomous Systems: Understanding People and their Impacts on Decision Making
-At my dissertation defense, I presented Planning and Recognition Together Close the Interaction Loop (PReTCIL) as one of the first ways to integrate algorithms from artificial intelligence (AI) planning and plan, activity, and intent recognition into a single method for adaptive closed-loop interaction in autonomous systems. Despite PReTCIL working out...
-
ChatGPT "passing" things: A(nother) story of cherry-picking, ignoring errors and hope
-In Nov 2022 OpenAI released the new ChatGPT language model, taking the world by storm with it. Today, we are flooded by tweets and articles claiming ChatGPT is reaching human-level performance in many tasks. But what tasks? Is ChatGPT ready to assist (or replace) humans? In this talk, we'll cover...
February
2022
October
September
June
-
Accelerating Research Software Understandability Through Knowledge Capture
-Research Software is key to understand, reproduce and reuse existing work in many disciplines, ranging from Geosciences to Astronomy or Artificial Intelligence. However, research software is usually difficult to find, reuse, compare and understand due to its disconnected documentation (dispersed in manuals, readme files, web sites, and code comments) and...
-
Decolonising science
-The phrase “decolonising the curriculum” very much seems like a buzzword, but what does it really mean? In particular, what does it mean for sciences? I intend to explore the background to “decolonising science”, address some of the issues that this raises, and look at some ideas which not only...
-
A Personal Perspective on Impact
-Most of our funders would like to see non-academic "impact" from the projects they support. In this talk, I'll give a personal perspective on impact, looking at both successes such as the Arria NLG spinout company and the simplenlg open-source package, and failures where expected impact did not materialise, such...
May
-
Representation Learning for Relational and Cross-Lingual Data
-Utilising real-world relational signals (e.g., structured knowledge) and understanding different languages are two (of the many) fundamental goals of Artificial General Intelligence. The corresponding explorations, however, have been relatively separate. In this talk, I will introduce our recent research outputs on bridging this gap: - We discovered the unnoticed connections between...
-
The challenge of adherence to digital healthcare - the case of ASICA
-Patient-directed digital healthcare delivery is becoming increasingly prominent and has received impetus from the recent COVID pandemic. Patient-directed digital healthcare is viewed positively by policy makers as a means to increase healthcare access, reduce costs and increase efficiency. Patient-directed digital healthcare also appears to be popular with certain patient groups....
April
March
-
Intention Progression in Multi-Agent Settings
-A key problem for rational agents is 'what do do next': which goal the agent should be trying to achieve, and which means it should use to achieve it. In the Belief-Desire-Intention approach to agents, this is termed the 'intention progression problem', and has largely been studied in a single...
-
Goal Recognition as Reinforcement Learning
-Most approaches for goal recognition rely on specifications of the possible dynamics of the actor in the environment when pursuing a goal. These specifications suffer from two key issues. First, encoding these dynamics requires careful design by a domain expert, which is often not robust to noise at recognition time....
February
-
Realising Accountability and Audit of AI Systems Using Knowledge Graphs
-To realise accountable AI systems, different types of information from a range of sources need to be recorded throughout the system life cycle. In the RAInS project, we argue that knowledge graphs can support capture and audit of such information; however, the creation of such accountability records must be planned...
-
Realising Accountability and Audit of AI Systems Using Knowledge Graphs
-To realise accountable AI systems, different types of information from a range of sources need to be recorded throughout the system life cycle. In the RAInS project, we argue that knowledge graphs can support capture and audit of such information; however, the creation of such accountability records must be planned...
-
Realising Accountability and Audit of AI Systems Using Knowledge Graphs
-To realise accountable AI systems, different types of information from a range of sources need to be recorded throughout the system life cycle. In the RAInS project, we argue that knowledge graphs can support capture and audit of such information; however, the creation of such accountability records must be planned...
2021
November
-
Machine Learning-based Anomaly Detection and Perturbation Analysis in Nuclear Reactors
-This talk will provide an overview and main results of a recently finished 4-year £5M EU-H2020 project (Sep 2017 – Aug 2021) entitled “Core Monitoring Techniques and Experimental Validation and Demonstration (Cortex - https://cortex-h2020.eu/)” that involved 20 partners from 11 countries (EU, Japan and US). Georgios was leading activities in...
-
Formal Argumentation, Dialogue, Users and Explanation
-In this talk I will describe several related strands of research around the use of argumentation and dialogue for human/machine interaction. These include its use in the context of explanation of program behaviour, as an explanatory mechanism for complex opaque systems such as planners and of computational reasoning process such...
October
-
Generating and Reasoning with Argumentation Graphs
-In argumentation theory, we study how to model reasoning through the construction and evaluation of arguments using, so called, argumentation semantics. However, this two steps process (generation and evaluation) have been shown to be limiting due to the large number of arguments generated from real-life knowledge bases. Moreover, although it...
-
CS Seminar: Evaluating Natural Language Generation
-A key challenge in Natural Language Generation (NLG) is evaluating the quality of texts produced by an NLG system. Robust and reliable evaluation is essential to determining whether a new NLG model or system advances state-of-the-art, understanding weaknesses of current NLG systems, and giving users a good understanding of what...
2018
September
May
2016
April
March
-
Computing Science Seminar. Moncur on"The role of digital technologies in transitional life events"
-Abstract: Digital technologies are now used across the human lifespan. In this seminar, I'll discuss my HCI research that explores the current roles of digital technologies across transitional human life events (becoming an adult, becoming a parent, breaking up, retiring, end of life ), and the ways in which digital technologies could be designed...
-
Computing Science Seminar. de Ruiter on "How Not to Study Interaction"
-Abstract: In this talk I will argue that human interaction cannot be studied properly using the standard experimental methods that have been successful in other areas of the cognitive sciences. Of the many problems with these methods, I will focus on two important ones: (a) the trade-off between experimental control and ecological validity, and (b) profound...
-
Computing Science Seminar. Rovatsos on "Diversity-Aware AI - the next frontier?"
-Abstract: Recently, AI has produced impressive advances mostly by following a "standard model" based on data-driven exploration of large solution spaces and optimisation toward a well-defined objective function. Arguably, this process model has little in common with human intelligence, where objectives are often vaguely defined and conflicting, satisficing behaviour is often...
2015
October
2014
August
July
2013
October
-
Joshi on "Penn Discourse Treebank and the Problem of Attribution"
-A presentation about the Penn Discourse Treebank
-
Caminada on "A Brief Overview of Formal Argumentation Theory"
-A presentation about formal argumentation theory.
-
Villazon-Terrazas on "Linked Enterprise Data - Iterative and Incremental Life Cycle"
-A presentation about Linked Data.
June
-
Computing Science Seminar by Ani Nenkova
-Emotion Analysis for Applications in Neuropsychiatry
-
Computing Science Seminar by Ani Nenkova
-Identifying Elements of Text Quality Automatically
-
Computing Science Seminar by Ani Nenkova
-Reassessing the state of the art in multi-document news summarization and its evaluation
May
April
-
Computing Science seminar by Christopher Brewster
-Linked Data and Semantic Technologies in Disasters and Food: Opportunities and Challenges
-
Computing Science seminar by Panos Alexopoulos
-Modelling Vagueness in Ontologies and Semantic Data: a Methodological Perspective
February
2012
December
September
June
May
-
Computing Science seminar by Margaret Mitchell
-Generating Descriptions of Images
-
Computing Science seminar by Sergio Sayago
-Human-Computer Interaction with older people through an ethnographical lens: everyday interactions with Information and Communication Technologies
-
Dynamics of neural networks
-School Seminar (NCS)
March
-
Computing Science seminar by Carron Shankland
-Direct evolution of process algebra model parameters
-
Computing Science Thesis presentation (year 2) by Michael Gibson
-A Knowledge-Based Approach to Multiplayer Action Games on Peer-to-Peer Networks
February
-
Computing Science seminar by Murdoch Gabbay
-You are not a number: how nameless foundations took over the world and made us think we have only numbers, and no names.
-
The Semantic Web: Ultimate Application for Natural Language Generation?
-School Seminar
-
Computing Science seminar by David Emele
-Title: Informing Dialogue Strategy through Argumentation-Derived Evidence
January
2011
November
-
Computing Science seminar by Per Ola Kristenssen
-Title: Designing text entry interfaces for society
-
Computing Science seminar by Thibaut Lust
-Title: Multiobjective combinatorial optimization: methods and applications