Searcharxiv⌕ Search

arXiv subjects

Alun Preece

Publications and source records attributed to Alun Preece.

43 records · Page 3Linked to original sources
arXiv2018

Stakeholders in Explainable AI

There is general consensus that it is important for artificial intelligence (AI) and machine learning systems to be explainable and/or interpretable. However, there is no general consensus over what is meant by 'explainable' and 'interpretable'. In this paper, we argue that this lack of consensus is due to there being several distinct stakeholder communities. We note that, while the concerns of the individual communities are broadly compatible, they are not identical, which gives rise to different intents and requirements for explainability/interpretability. We use the software engineering distinction between validation and verification, and the epistemological distinctions between knowns/unknowns, to tease apart the concerns of the stakeholder communities and highlight the areas where their foci overlap or diverge. It is not the purpose of the authors of this paper to 'take sides' - we count ourselves as members, to varying degrees, of multiple communities - but rather to help disambiguate what stakeholders mean when they ask 'Why?' of an AI.

cs.AI↗
arXiv2018

Defining the Collective Intelligence Supply Chain

Organisations are increasingly open to scrutiny, and need to be able to prove that they operate in a fair and ethical way. Accountability should extend to the production and use of the data and knowledge assets used in AI systems, as it would for any raw material or process used in production of physical goods. This paper considers collective intelligence, comprising data and knowledge generated by crowd-sourced workforces, which can be used as core components of AI systems. A proposal is made for the development of a supply chain model for tracking the creation and use of crowdsourced collective intelligence assets, with a blockchain based decentralised architecture identified as an appropriate means of providing validation, accountability and fairness.

cs.AI↗
arXiv2018

Uncertainty Aware AI ML: Why and How

This paper argues the need for research to realize uncertainty-aware artificial intelligence and machine learning (AI\&ML) systems for decision support by describing a number of motivating scenarios. Furthermore, the paper defines uncertainty-awareness and lays out the challenges along with surveying some promising research directions. A theoretical demonstration illustrates how two emerging uncertainty-aware ML and AI technologies could be integrated and be of value for a route planning operation.

cs.AI↗
arXiv2018

Interpretable to Whom? A Role-based Model for Analyzing Interpretable Machine Learning Systems

Several researchers have argued that a machine learning system's interpretability should be defined in relation to a specific agent or task: we should not ask if the system is interpretable, but to whom is it interpretable. We describe a model intended to help answer this question, by identifying different roles that agents can fulfill in relation to the machine learning system. We illustrate the use of our model in a variety of scenarios, exploring how an agent's role influences its goals, and the implications for defining interpretability. Finally, we make suggestions for how our model could be useful to interpretability researchers, system developers, and regulatory bodies auditing machine learning systems.

cs.AI↗
arXiv2014

Conversational Sensing

Recent developments in sensing technologies, mobile devices and context-aware user interfaces have made it possible to represent information fusion and situational awareness as a conversational process among actors - human and machine agents - at or near the tactical edges of a network. Motivated by use cases in the domain of security, policing and emergency response, this paper presents an approach to information collection, fusion and sense-making based on the use of natural language (NL) and controlled natural language (CNL) to support richer forms of human-machine interaction. The approach uses a conversational protocol to facilitate a flow of collaborative messages from NL to CNL and back again in support of interactions such as: turning eyewitness reports from human observers into actionable information (from both trained and untrained sources); fusing information from humans and physical sensors (with associated quality metadata); and assisting human analysts to make the best use of available sensing assets in an area of interest (governed by management and security policies). CNL is used as a common formal knowledge representation for both machine and human agents to support reasoning, semantic information fusion and generation of rationale for inferences, in ways that remain transparent to human users. Examples are provided of various alternative styles for user feedback, including NL, CNL and graphical feedback. A pilot experiment with human subjects shows that a prototype conversational agent is able to gather usable CNL information from untrained human subjects.

cs.HC↗
arXiv2011

Rule-Based Semantic Sensing

Rule-Based Systems have been in use for decades to solve a variety of problems but not in the sensor informatics domain. Rules aid the aggregation of low-level sensor readings to form a more complete picture of the real world and help to address 10 identified challenges for sensor network middleware. This paper presents the reader with an overview of a system architecture and a pilot application to demonstrate the usefulness of a system integrating rules with sensor middleware.

cs.AI↗