Welcome to Research Commons

Research Commons is the University of Waikato's open access research repository, housing research publications and theses produced by the University's staff and students.

Communities in Research Commons

Select a community to browse its collections.

Now showing 1 - 2 of 2

Recent Submissions

The Algorithmic Brush: How is AI affecting the social foundations of creativity?
(2026) Schott, Gareth R.
Artificial intelligence is rapidly changing the way we create, design and understand images — but what happens to creativity when the tools themselves begin to think, generate and make? The Algorithmic Brush explores AI’s growing role in art and design, asking broader questions about authorship, originality, creative labour and the social foundations of artistic practice. Rather than focusing only on what AI can produce, the discussion considers what its emergence means for the people, communities and cultural systems that have traditionally shaped creativity. Professor Gareth Schott of the University of Waikato brings together his academic research and experience as an artist to examine the opportunities, tensions and uncertainties surrounding AI and creative practice. A conversation about technology, creativity and what it means to be human in an increasingly algorithmic creative world.
Rethinking memory in continual learning: Beyond a monolithic store of the past
(TMLR, 2025) Zhang, Yaqian; Pfahringer, Bernhard; Frank, Eibe; Bifet, Albert
Memory is a critical component in replay-based continual learning (CL). Prior research has largely treated CL memory as a monolithic store of past data, focusing on how to select and store representative past examples. However, this perspective overlooks the higher-level memory architecture that governs the interaction between old and new data. In this work, we identify and characterize a dual-memory system that is inherently present in both online and offline CL settings. This system comprises: a short-term memory, which temporarily buffers recent data for immediate model updates, and a long-term memory, which maintains a carefully curated subset of past experiences for future replay and consolidation. We propose memory capacity ratio (MCR), the ratio between short-term memory and long-term memory capacities, to characterize online and offline CL. Based on this framework, we systematically investigate how MCR influences generalization, stability, and plasticity. Across diverse CL settings—class-incremental, task-incremental, and domain-incremental—and multiple data modalities (e.g., image and text classification), we observe that a smaller MCR, characteristic of online CL, can yield comparable or even superior performance relative to a larger one, characteristic of offline CL, when both are evaluated under equivalent computational and data storage budgets. This advantage holds consistently across several state-of-the-art replay strategies, such as ER, DER, and SCR. Theoretical analysis further reveals that a reduced MCR yields a better trade-off between stability and plasticity by lowering a bound on generalization error when learning from non-stationary data streams with limited memory. These findings offer new insights into the role of memory allocation in continual learning and underscore the underexplored potential of online CL approaches.
BELLA: Black-box model explanations by local linear approximations
(TMLR, 2025) Radulović, Nedeljko; Bifet, Albert; Suchanek, Fabian M.
Understanding the decision-making process of black-box models has become not just a legal requirement, but also an additional way to assess their performance. However, the state of the art post-hoc explanation approaches for regression models rely on synthetic data generation, which introduces uncertainty and can hurt the reliability of the explanations. Furthermore, they tend to produce explanations that apply to only very few data points. In this paper, we present BELLA, a deterministic model-agnostic post-hoc approach for explaining the individual predictions of regression black-box models. BELLA provides explanations in the form of a linear model trained in the feature space. BELLA maximizes the size of the neighborhood to which the linear model applies so that the explanations are accurate, simple, general, and robust.
We never went to the supermarket: A whanau oral history in kai reclamation in the Waipā
(The University of Waikato, 2025) Clarke, Reese; Ringham, Sandra Lee
Food is an essential part of life and identity; kai forms the foundations of our relationships with one another and with the natural world. In this research I explore my whānau relationship with kai and kai sovereignty to better understand long lasting effects of urbanisation, industrialisation and colonisation. This thesis centres oral histories and lived experiences of multiple generations of my whānau, from the 1950 onwards. This research comes from a personal desire to understand the roots of my relationship with kai and my Māori identity. By examining the forces that have reshaped the Waipā into a farming dominated landscape, I consider the impacts of colonisation on mahinga kai practices and in turn on kai sovereignty within my own life and that of my whānau. Through these intergenerational kōrero, I highlight that kai sovereignty is not only a critical response to food insecurity, but also a pathway toward cultural renewal, strengthened autonomy, and collective wellbeing. Although kai sovereignty is grounded in community driven systems and shared reasonability, it is equally enacted through small, everyday practices, gardening, cooking, hunting, fishing sharing kai and other activities that sustain māuranga, reinforce whanaungatanga and reaffirm Māori self-determination over the ways we gather grow, prepare and value our kai.
A dangerous turn: The confluence of safety and citizenship discourses in educational scholarship
(Taylor & Francis, 2025-01-05) Estellés, Marta
In recent decades, calls to foster safe learning environments have proliferated in the educational scholarship related to citizenship. Examples range from demands to keep young citizens safe in the digital world through to calls to hold safe conversations around controversial issues. These invocations of safety, however, have raised little opposition and debate. Using a Foucauldian lens, this article examines the ‘truths’ that underlie the discourses of safety and citizenship in the educational scholarship published from 2012 to 2022. In the 103 articles discursively analyzed, assumptions such as safety as an educational right, students as vulnerable objects of protection and teachers as safety providers are identified. The (dangerous) implications of these assumptions are critically discussed.