Now showing 1 - 10 of 35
  • Publication
    The Twin-System Approach as One Generic Solution for XAI: An Overview of ANN-CBR Twins for Explaining Deep Learning
    The notion of twin-systems is proposed to address the eXplainable AI (XAI) problem, where an uninterpretable black-box system is mapped to a white-box “twin” that is more interpretable. In this short paper, we overview very recent work that advances a generic solution to the XAI problem, the so-called twin-system approach. The most popular twinning in the literature is that between an Artificial Neural Networks (ANN1) as a black box and Case Based Reasoning (CBR) system as a white-box, where the latter acts as an interpretable proxy for the former. We outline how recent work reviving this idea has applied it to deep learning methods. Furthermore, we detail the many fruitful directions in which this work may be taken; such as, determining the most (i) accurate feature-weighting methods to be used, (ii) appropriate deployments for explanatory cases, (iii) useful cases of explanatory value to users.
  • Publication
    On Supporting Digital Journalism: Case Studies in Co-Designing Journalistic Tools
    Since 2013 researchers at University College Dublin in the Insight Centre for Data Analytics have been involved in a significant research programme in digital journalism, specifically targeting tools and social media guidelines to support the work of journalists. Most of this programme was undertaken in collaboration with The Irish Times. This collaboration involved identifying key problems currently faced by digital journalists, developing tools as solutions to these problems, and then iteratively co-designing these tools with feedback from journalists. This paper reports on our experiences and learnings from this research programme, with a view to informing similar efforts in the future.
  • Publication
    The Illusionary Comfort of a Warm Normative Theory
    (Cognition, Language and Perception Research Group, 2017-11-24)
    One of the most common tactics in Cognitive Science is the wholesale adoption of anexisting normative account as a theoretical basis for understanding some aspect ofhuman cognition or, indeed, as a yardstick for correct behaviour (see e.g., Eysenck & Keane, 1995, 2015). Research on the psychology of deduction (Johnson-Laird, 1999;Johnson-Laird & Byrne, 1991; Evans, Newstead & Byrne, 1993; Oaksford & Chater,1998, 2007) has some of the most well-known examples of this tactic, where logicismhas argued that human thinking (1) reflects some internalized form of extensional,classical logic and (2) should be measured against classical logic as a normativesystem (Elquyam & Evans, 2011, pp. 234). Similarly, Oaksford & Chater (2007)advance Bayesian probability theory as a normative account of human rationality,though many disagree (Jones & Love, 2011; Bowers & Davis, 2012).
  • Publication
    A neural network model of Irish farmers perceptions of land mobility
    Land has always been one of the most important and controversial assets in Ireland and land mobility continues to be a critical issue to the future success of the Irish agricultural sector (FH2020). The Irish agricultural sector is still portrayed by a low level of land mobility and late transfer pattern with small farms and an older farming population. Policies and schemes applied to the agricultural sector to improve land mobility situation appear to be failing to have the desired effect. The overall objective of this study is to assess the present situation and identify potential solutions that could improve land mobility and smooth land transfer in the Irish agricultural sector as perceived by the Irish farmer.
  • Publication
    The Unexpected Unexpected and the Expected Unexpected: How People's Conception of the Unexpected is Not That Unexpected
    The answers people give when asked to “think of the unexpected” for everyday event scenarios appear to be more expected than unexpected. There are expected unexpected outcomes that closely adhere to the given information in ascenario, based on familiar disruptions and common plan-failures.There are also unexpected unexpected outcomesthat are more inventive, that depart from given information, adding new concepts/actions. However, people seem to tend to conceive of the unexpected as the former more than the latter. Study 1 tests these proposals by analysing the object-concepts people mention in their reports of the unexpected and the agreement between their answers. Study 2 shows that object-choices are weakly influenced by recency, that is, the order of sentences in the scenario. The implications of these results for ideas in philosophy, psychology and computing are discussed.
  • Publication
    Bayesian Case-Exclusion and Explainable AI (XAI) for Sustainable Farming
    Smart agriculture (SmartAg) has emerged as a rich domain for AI-driven decision support systems (DSS); however, it is often challenged by user-adoption issues. This paper reports a case-based reasoning system, PBI-CBR, that predicts grass growth for dairy farmers, that combines predictive accuracy and explanations to improve user adoption. PBI-CBR’s key novelty is its use of Bayesian methods for case-base maintenance in a regression domain. Experiments report the tradeoff between predictive accuracy and explanatory capability for different variants of PBI-CBR, and how updating Bayesian priors each year improves performance.
  • Publication
    Triangulating Surprise: Expectations, Uncertainty, and Making Sense
    (Cognitive Science Society and Curran Associates, Inc., 2014-07-26) ; ; ;
    Surprise is a ubiquitous phenomenon that both draws on cognition and affects cognition, in a number of different ways. For example, in artificial intelligence an agent in a changing and imperfectly-known environment has been argued to need a surprise mechanism to survive. This symposium brings together researchers in education, computer science, cognitive psychology, and business to explore the relationship between surprise and cognition, and how it might be harnessed across domains. We will open with a touchstone challenge: How can surprising information be recruited to promote learning? (Munnich & Ranney) Then we will explore several perspectives on surprise, ranging from violation of expectations created through repetition (Loewenstein) to a focus on the information content of surprising events (Maguire & Maguire), to the apparently conflicting roles surprise may play in judgment (May, Smith-Rodden, & Ash). Our final speakers (Foster & Keane) will synthesize these approaches, and present a broad framework for future research on surprise within the cognitive sciences.
  • Publication
    Creativity: A Gap Analysis
    Arguably, our current understanding of creativity has a few gaps that might benefit from some analysis. In the paper, I review the main empirical findings and theoretical proposals on the core cognitive processes of creative thinking, outlining some of the deficiencies therein. I then develop a meta-analysis of the interactions between the main components of the creative universe; namely, the World, Language and Experience. In this analysis, I try to show that creativity often emerges at the interstices between some aspect of the World and our Experience (our understanding of the World), or some aspect of the World and Language (our linguistic descriptions of that World), or some aspect our Experience and Language. To demonstrate these points, I use this analysis to explain the emergence of extreme literary creativity in Ireland at the turn of the last century. More generally, it is hoped that this analysis offers a new perspective on all aspects of creativity and how they might be approached.
  • Publication
    The effect of soft, modal and loud voice levels on entrainment in noisy conditions
    Conversation partners have a tendency to adapt their vocal intensity to each other and to other social and environmental factors. A socially adequate vocal intensity level by a speech synthesiser that goes beyond mere volume adjustment is highly desirable for a rewarding and successful human-machine or machine mediated human-human interaction. This paper examines the interaction of the Lombard effect and speaker entrainment in a controlled experiment conducted with a confederate interlocutor. The interlocutor was asked to maintain either a soft, a modal or a loud voice level during the dialogues. Through half of the trials, subjects were exposed to a cocktail party noise through headphones. The analytical results suggest that both the background noise and the interlocutors voice level affect the dynamics of speaker entrainment. Speakers appear to still entrain to the voice level of their interlocutor in noisy conditions, though to a lesser extent, as strategies of ensuring intelligibility affect voice levels as well. These findings could be leveraged in spoken dialogue systems and speech generating devices to help choose a vocal effort level for the synthetic voice that is both intelligible and socially suited to a specific interaction.
  • Publication
    Surprise! You've Got Some Explaining to Do...
    (Cognitive Science Society, 2013-08-03) ;
    Why are some events more surprising than others? We propose that events that are more difficult to explain are those that are more surprising. The two experiments reported here test the impact of different event outcomes (Outcome-Type) and task demands (Task) on ratings of surprise for simple story scenarios. For the Outcome-Type variable, participants saw outcomes that were either knownor less-knownsurprising outcomes for each scenario. For the Task variable, participants either answered comprehension questions or provided an explanation of the outcome. Outcome-Type reliably affected surprise judgments; known outcomes were rated as less surprising than less-known outcomes. Task also reliably affected surprise judgments; when people provided an explanation it lowered surprise judgments relative to simply answering comprehension questions. Both experiments thus provide evidence on this less-explored explanation aspect of surprise, specifically showing that ease of explanation is a key factor in determining the level of surprise experienced