More than half of undergraduates say they consult artificial intelligence programmes to help with their essays, while schools are trialling its use in the classroom. A survey of more than 1,000 UK undergraduates, conducted by the Higher Education Policy Institute (Hepi), found 53% were using AI to generate material for work they would be marked on. One in four are using applications such as Google Bard or ChatGPT to suggest topics and one in eight are using them to create content. Just 5% admitted to copying and pasting unedited AI-generated text into their assessments. Teachers are also seeking to use AI to streamline their work, with the Education Endowment Foundation (EEF) signing up secondary schools for a new research project into the use of AI to generate lesson plans and teaching materials as well as exams and model answers.

Alan Turing proposed in 1950 a framework called an imitation game to decide if a machine could think. Using mathematics developed largely after Turing -- category theory -- we analyze a broader class of universal imitation games (UIGs), which includes static, dynamic, and evolutionary games. In static games, the participants are in a steady state. In dynamic UIGs, "learner" participants are trying to imitate "teacher" participants over the long run. In evolutionary UIGs, the participants are competing against each other in an evolutionary game, and participants can go extinct and be replaced by others with higher fitness. We use the framework of category theory -- in particular, two influential results by Yoneda -- to characterize each type of imitation game. Universal properties in categories are defined by initial and final objects. We characterize dynamic UIGs where participants are learning by inductive inference as initial algebras over well-founded sets, and contrast them with participants learning by conductive inference over the final coalgebra of non-well-founded sets. We briefly discuss the extension of our categorical framework for UIGs to imitation games on quantum computers.

In this paper we revisit the efficacy of knowledge distillation as a function matching and metric learning problem. In doing so we verify three important design decisions, namely the normalisation, soft maximum function, and projection layers as key ingredients. We theoretically show that the projector implicitly encodes information on past examples, enabling relational gradients for the student. We then show that the normalisation of representations is tightly coupled with the training dynamics of this projector, which can have a large impact on the students performance. Finally, we show that a simple soft maximum function can be used to address any significant capacity gap problems. Experimental results on various benchmark datasets demonstrate that using these insights can lead to superior or comparable performance to state-of-the-art knowledge distillation techniques, despite being much more computationally efficient. In particular, we obtain these results across image classification (CIFAR100 and ImageNet), object detection (COCO2017), and on more difficult distillation objectives, such as training data efficient transformers, whereby we attain a 77.2% top-1 accuracy with DeiT-Ti on ImageNet. Code and models are publicly available.

Understanding the importance of the inputs on the output is useful across many tasks. This work provides an information-theoretic framework to analyse the influence of inputs for text classification tasks. Natural language processing (NLP) tasks take either a single element input or multiple element inputs to predict an output variable, where an element is a block of text. Each text element has two components: an associated semantic meaning and a linguistic realization. Multiple-choice reading comprehension (MCRC) and sentiment classification (SC) are selected to showcase the framework. For MCRC, it is found that the context influence on the output compared to the question influence reduces on more challenging datasets. In particular, more challenging contexts allow a greater variation in complexity of questions. Hence, test creators need to carefully consider the choice of the context when designing multiple-choice questions for assessment. For SC, it is found the semantic meaning of the input text dominates (above 80\% for all datasets considered) compared to its linguistic realisation when determining the sentiment. The framework is made available at: https://github.com/WangLuran/nlp-element-influence

Classic Delphi and Fuzzy Delphi methods are used to test content validity of data collection tools such as questionnaires. Fuzzy Delphi takes the opinion issued by judges from a linguistic perspective reducing ambiguity in opinions by using fuzzy numbers. We propose an extension named 2-Tuple Fuzzy Linguistic Delphi method to deal with scenarios in which judges show different expertise degrees by using fuzzy multigranular semantics of the linguistic terms and to obtain intermediate and final results expressed by 2-tuple linguistic values. The key idea of our proposal is to validate the full questionnaire by means of the evaluation of its parts, defining the validity of each item as a Decision Making problem. Taking the opinion of experts, we measure the degree of consensus, the degree of consistency, and the linguistic score of each item, in order to detect those items that affect, positively or negatively, the quality of the instrument. Considering the real need to evaluate a b-learning educational experience with a consensual questionnaire, we present a Decision Making model for questionnaire validation that solves it. Additionally, we contribute to this consensus reaching problem by developing an online tool under GPL v3 license. The software visualizes the collective valuations for each iteration and assists to determine which parts of the questionnaire should be modified to reach a consensual solution.

This survey paper provides a comprehensive analysis of big data algorithms in recommendation systems, addressing the lack of depth and precision in existing literature. It proposes a two-pronged approach: a thorough analysis of current algorithms and a novel, hierarchical taxonomy for precise categorization. The taxonomy is based on a tri-level hierarchy, starting with the methodology category and narrowing down to specific techniques. Such a framework allows for a structured and comprehensive classification of algorithms, assisting researchers in understanding the interrelationships among diverse algorithms and techniques. Covering a wide range of algorithms, this taxonomy first categorizes algorithms into four main analysis types: User and Item Similarity-Based Methods, Hybrid and Combined Approaches, Deep Learning and Algorithmic Methods, and Mathematical Modeling Methods, with further subdivisions into sub-categories and techniques. The paper incorporates both empirical and experimental evaluations to differentiate between the techniques. The empirical evaluation ranks the techniques based on four criteria. The experimental assessments rank the algorithms that belong to the same category, sub-category, technique, and sub-technique. Also, the paper illuminates the future prospects of big data techniques in recommendation systems, underscoring potential advancements and opportunities for further research in this field

Spiking Neural Networks (SNNs), providing more realistic neuronal dynamics, have shown to achieve performance comparable to Artificial Neural Networks (ANNs) in several machine learning tasks. Information is processed as spikes within SNNs in an event-based mechanism that significantly reduces energy consumption. However, training SNNs is challenging due to the non-differentiable nature of the spiking mechanism. Traditional approaches, such as Backpropagation Through Time (BPTT), have shown effectiveness but comes with additional computational and memory costs and are biologically implausible. In contrast, recent works propose alternative learning methods with varying degrees of locality, demonstrating success in classification tasks. In this work, we show that these methods share similarities during the training process, while they present a trade-off between biological plausibility and performance. Further, this research examines the implicitly recurrent nature of SNNs and investigates the influence of addition of explicit recurrence to SNNs. We experimentally prove that the addition of explicit recurrent weights enhances the robustness of SNNs. We also investigate the performance of local learning methods under gradient and non-gradient based adversarial attacks.

Large Language Model (LLM) leaderboards based on benchmark rankings are regularly used to guide practitioners in model selection. Often, the published leaderboard rankings are taken at face value - we show this is a (potentially costly) mistake. Under existing leaderboards, the relative performance of LLMs is highly sensitive to (often minute) details. We show that for popular multiple choice question benchmarks (e.g. MMLU) minor perturbations to the benchmark, such as changing the order of choices or the method of answer selection, result in changes in rankings up to 8 positions. We explain this phenomenon by conducting systematic experiments over three broad categories of benchmark perturbations and identifying the sources of this behavior. Our analysis results in several best-practice recommendations, including the advantage of a hybrid scoring method for answer selection. Our study highlights the dangers of relying on simple benchmark evaluations and charts the path for more robust evaluation schemes on the existing benchmarks.

This study explores the use of Generative AI chatbots for transforming public science exhibits into virtual experiences that can extend the engagement of exhibits into the classroom. The broader goal is to increase accessibility of science exhibits, especially for those marginalized in STEM due to various factors, including cultural barriers. We hypothesize that turning exhibits into first-person anthropomorphized chatbots with a personality, like quirky-talking asteroids or comets, can increase engagement and learning. The paper mainly explores if such techniques are possible using Generative AI (e.g. GPT) via prompt engineering alone. The research includes an investigation into the possibility of integrating interactive assessment via question-generation using Bloom's Taxonomy. Initial results indicate that it is possible to combine these techniques. As such, it lays a foundation for future classroom evaluations of such chatbots to gauge their overall efficacy in extending the reach of science exhibitions. The paper concludes by discussing extensions of the research to fully evaluate effectiveness in virtual field-trips. We also include a brief examination of additional ways to enhance student motivation towards learning via chatbots.

We study the problem of online uncertainty quantification, such as that encountered in time-series forecasting. Our goal is to produce a prediction set at each time, based on all previous information, that contain the true label with a specified coverage probability. Such prediction sets are useful to the point of being requirements in many sequential problems, including medicine [Robinson, 1978], robotics [Lindemann et al., 2023], finance [Mykland, 2003], and epidemiology [Cramer et al., 2022]. Given this broad utility, it comes as no surprise that prediction sets have been studied for approximately one hundred years (and possibly more; see Section 1.1 of Tian et al. [2022]).