A5012388184- Semantic Web and Ontologies
- Service-Oriented Architecture and Web Services
- Explainable Artificial Intelligence (XAI)
- Complex Network Analysis Techniques
- Bayesian Modeling and Causal Inference
- Natural Language Processing Techniques
- Opinion Dynamics and Social Influence
- AI-based Problem Solving and Planning
- Speech and dialogue systems
- Adversarial Robustness in Machine Learning
- Data Quality and Management
- Logic, Reasoning, and Knowledge
- Advanced Graph Neural Networks
- Human-Automation Interaction and Safety
- Evolutionary Game Theory and Cooperation
- Advanced Database Systems and Queries
- Scientific Computing and Data Management
- Topic Modeling
- Cognitive Science and Mapping
- Wikis in Education and Collaboration
- Complex Systems and Decision Making
- Team Dynamics and Performance
- Anomaly Detection Techniques and Applications
- Multi-Agent Systems and Negotiation
- Auction Theory and Applications
IBM (United Kingdom)
2012-2021
Cardiff University
2017-2021
IBM (United States)
2008-2018
University of Southampton
2008-2009
Deep neural networks have achieved near-human accuracy levels in various types of classification and prediction tasks including images, text, speech, video data. However, the continue to be treated mostly as black-box function approximators, mapping a given input output. The next step this human-machine evolutionary process - incorporating these into mission critical processes such medical diagnosis, planning control requires level trust association with machine Typically, statistical...
During Fusion 2019 Conference (https://www.fusion2019.org/program.html), leading experts presented ideas on the historical, contemporary, and future coordination of artificial intelligence/machine learning (AI/ML) with sensor data fusion (SDF). While AI/ML SDF concepts have had a rich history since early 1900s—emerging from philosophy psychology—it was not until dawn computers that both researchers initiated discussions how mathematical techniques could be implemented for real-time analysis....
There is general consensus that it important for artificial intelligence (AI) and machine learning systems to be explainable and/or interpretable. However, there no over what meant by 'explainable' 'interpretable'. In this paper, we argue lack of due being several distinct stakeholder communities. We note that, while the concerns individual communities are broadly compatible, they not identical, which gives rise different intents requirements explainability/interpretability. use software...
Several researchers have argued that a machine learning system's interpretability should be defined in relation to specific agent or task: we not ask if the system is interpretable, but whom it interpretable. We describe model intended help answer this question, by identifying different roles agents can fulfill system. illustrate use of our variety scenarios, exploring how an agent's role influences its goals, and implications for defining interpretability. Finally, make suggestions could...
Machine learning systems can provide outstanding results, but their black-box nature means that it's hard to understand how the conclusion has been reached. Understanding results are determined is especially important in military and security contexts due importance of decisions may be made as a result. In this work, reliability LIME (Local Interpretable Model Agnostic Explanations), method interpretability, was analyzed developed. A simple Convolutional Neural Network (CNN) model trained...
Learning network representation has a variety of applications, such as classification. Most existing work in this area focuses on static undirected networks and does not account for presence directed edges or temporal changes. Furthermore, most node representations that do poorly tasks like In paper, we propose novel embedding methodology, gl2vec, classification both networks. gl2vec constructs vectors feature using graphlet distributions null model comparing them against random graphs. We...
Controlled natural language (CNL) has great potential to support human-machine interaction (HMI) because it provides an information representation that is both human readable and machine processable. We investigated the effectiveness of a CNL-based conversational interface for HMI in behavioral experiment called simple regarding locally observed collective knowledge (SHERLOCK). In SHERLOCK, individuals acted groups discover report using (NL), which then processed into CNL. The fused...
Controlled English is a human-readable information representation format that implemented using restricted subset of the language, but which unambiguous and directly accessible by simple machine processes. We have been researching capabilities CE in number contexts, exploring degree to flexible more human-friendly could aid intelligence analyst multi-agent collaborative operational environment; especially cases where agents are mixture other human users processes aimed at assisting users....
The term cognitive computing (CC) refers to computer systems that harness multiple techniques from artificial intelligence (AI) and signal processing (SP). Situational understanding (SU) involves creating reasoning about models of an environment events. Coalition operations are defined by partners seeking achieve a common purpose. This paper characterises the SU problem in coalition context - situational (CSU) terms set attributes. argues CSU problems require CC system solutions involving...
In domains such as emergency response, environmental monitoring, policing and security, sensor information networks are deployed to assist human users across multiple agencies conduct missions at or near the 'front line'. These present challenging problems in terms of human-machine collaboration: need task network help them achieve mission objectives, while humans (sometimes same individuals) also sources mission-critical information. We propose a natural language-based conversational...
Situational understanding (SU) requires a combination of insight - the ability to accurately perceive an existing situation and foresight anticipate how may develop in future. SU involves information fusion as well model representation inference. Commonly, heterogenous data sources must be exploited process: often including both hard soft products. In coalition context, processing resources will also distributed subjected restrictions on sharing. It necessary for human loop processes,...
Abstract In elite sports, there is an opportunity to take advantage of rich and detailed datasets generated across multiple threads the sporting business. Challenges currently exist due time constraints analyse data, as well quantity variety data available assess. Artificial Intelligence (AI) techniques can be a valuable asset in assisting decision makers tackling such challenges, but deep AI skills are generally not held by those with experience domains. Here, we describe how certain...