What the #®¥§≠$@ is Creativity?

Creativity is The Holy Grail of the Cognitive Sciences and it is very important for researchers in the Computer Sciences and AI fields. Although all attempts to explain and replicate intelligence have so far failed, the quest remains a key part of their research. This paper takes two innovative approaches. First, we see cognitive processes as involving rule-followingand as flexible, even chaotic, heuristics. This first concept uses a multi-heuristic concept without any complexes as mixed-cognition. Second, we propose abduction which, though seldom employed in this specific debate, is nonetheless a good way to explore creativity. Using both strategies, along with analysis of specific human creativity cases, we suggesta new cognitive paradigm that is both more realistic and truthful than hitherto. The idea is to offer a new way to achieve more powerful, complex artificial reasoning systems.

A win-win scenario? Restrictive policies from alternative standpoints

PurposeIn this viewpoint article, the authors consider the challenges in implementing restrictive policies, with a particular focus on how these policies are experienced, in practice, from alternative standpoints.Design/methodology/approachThe authors draw on social science studies of decommissioning work to highlight how patient and official versions of value often vary, creating difficulties and distrust as restrictive policies are implemented. Patients and the public are well aware that financial calculations are somehow embedded in concepts of “evidence” and “value” but are usually unfamiliar with the social infrastructures that produce and utilise such concepts. The authors discuss with reference to a contemporary restrictive programme in England.FindingsWhile policymakers and researchers frequently present restrictive policies as “win-win” scenarios (achieving both cost-savings for healthcare services and improved patient care), social science analyses highlight the potential for tensions and controversies between stakeholders. The authors recognise that cost containment is a necessary component of policymaking work but argue that policymakers and researchers should seek to map (and make visible) the socially organised reasoning, systems and processes that are involved in enacting restrictive policies. Although transparency may pose challenges, it is important for informed democratic engagement, allowing legitimate scrutiny of whose voices are being heard and interests served (the “winners” and “losers”).Originality/valueThe authors argue for social science analyses that explore overuse, value and restrictive practices from alternative (e.g. patient) standpoints. These can provide important insights to help identify priorities for intervention and support better communication.

Declarative Algorithms and Complexity Results for Assumption-Based Argumentation

The study of computational models for argumentation is a vibrant area of artificial intelligence and, in particular, knowledge representation and reasoning research. Arguments most often have an intrinsic structure made explicit through derivations from more basic structures. Computational models for structured argumentation enable making the internal structure of arguments explicit. Assumption-based argumentation (ABA) is a central structured formalism for argumentation in AI. In this article, we make both algorithmic and complexity-theoretic advances in the study of ABA. In terms of algorithms, we propose a new approach to reasoning in a commonly studied fragment of ABA (namely the logic programming fragment) with and without preferences. While previous approaches to reasoning over ABA frameworks apply either specialized algorithms or translate ABA reasoning to reasoning over abstract argumentation frameworks, we develop a direct declarative approach to ABA reasoning by encoding ABA reasoning tasks in answer set programming. We show via an extensive empirical evaluation that our approach significantly improves on the empirical performance of current ABA reasoning systems. In terms of computational complexity, while the complexity of reasoning over ABA frameworks is well-understood, the complexity of reasoning in the ABA+ formalism integrating preferences into ABA is currently not fully established. Towards bridging this gap, our results suggest that the integration of preferential information into ABA via so-called reverse attacks results in increased problem complexity for several central argumentation semantics.

Modular design patterns for hybrid learning and reasoning systems

The unification of statistical (data-driven) and symbolic (knowledge-driven) methods is widely recognized as one of the key challenges of modern AI. Recent years have seen a large number of publications on such hybrid neuro-symbolic AI systems. That rapidly growing literature is highly diverse, mostly empirical, and is lacking a unifying view of the large variety of these hybrid systems. In this paper, we analyze a large body of recent literature and we propose a set of modular design patterns for such hybrid, neuro-symbolic systems. We are able to describe the architecture of a very large number of hybrid systems by composing only a small set of elementary patterns as building blocks. The main contributions of this paper are: 1) a taxonomically organised vocabulary to describe both processes and data structures used in hybrid systems; 2) a set of 15+ design patterns for hybrid AI systems organized in a set of elementary patterns and a set of compositional patterns; 3) an application of these design patterns in two realistic use-cases for hybrid AI systems. Our patterns reveal similarities between systems that were not recognized until now. Finally, our design patterns extend and refine Kautz’s earlier attempt at categorizing neuro-symbolic architectures.

Approximate reasoning with fuzzy rule interpolation: background and recent advances

Approximate reasoning systems facilitate fuzzy inference through activating fuzzy if–then rules in which attribute values are imprecisely described. Fuzzy rule interpolation (FRI) supports such reasoning with sparse rule bases where certain observations may not match any existing fuzzy rules, through manipulation of rules that bear similarity with an unmatched observation. This differs from classical rule-based inference that requires direct pattern matching between observations and the given rules. FRI techniques have been continuously investigated for decades, resulting in various types of approach. Traditionally, it is typically assumed that all antecedent attributes in the rules are of equal significance in deriving the consequents. Recent studies have shown significant interest in developing enhanced FRI mechanisms where the rule antecedent attributes are associated with relative weights, signifying their different importance levels in influencing the generation of the conclusion, thereby improving the interpolation performance. This survey presents a systematic review of both traditional and recently developed FRI methodologies, categorised accordingly into two major groups: FRI with non-weighted rules and FRI with weighted rules. It introduces, and analyses, a range of commonly used representatives chosen from each of the two categories, offering a comprehensive tutorial for this important soft computing approach to rule-based inference. A comparative analysis of different FRI techniques is provided both within each category and between the two, highlighting the main strengths and limitations while applying such FRI mechanisms to different problems. Furthermore, commonly adopted criteria for FRI algorithm evaluation are outlined, and recent developments on weighted FRI methods are presented in a unified pseudo-code form, easing their understanding and facilitating their comparisons.

Ballot spoilage as a response to limitations on choice and influence

Electoral systems vary in terms of the choice and influence they offer voters. Beyond selecting between parties, preferential systems allow for choices within parties. More proportional systems make it likely that influence over who determines the assembly’s majority will be distributed across relatively more voters. In response to systems that limit choice and influence, we hypothesize that voters will cast more blank, null, or spoiled ballots on purpose. We use a regression discontinuity opportunity in French municipal elections to test this hypothesis. An exogenously chosen and arbitrary cutpoint is used to determine the electoral rules municipalities use to select their assemblies. We find support for our reasoning—systems that do not allow intraparty preference votes and that lead to disproportional outcomes provoke vote spoilage. Rates of vote spoilage are frequently sufficient to change control over the assembly if those votes had instead been cast validly for the second-place party.