Tommi Kärkkäinen

Shiwei Liu, Tianlong Chen, Xiaohan Chen et al.

Transformers have quickly shined in the computer vision world since the emergence of Vision Transformers (ViTs). The dominant role of convolutional neural networks (CNNs) seems to be challenged by increasingly effective transformer-based models. Very recently, a couple of advanced convolutional models strike back with large kernels motivated by the local-window attention mechanism, showing appealing performance and efficiency. While one of them, i.e. RepLKNet, impressively manages to scale the kernel size to 31x31 with improved performance, the performance starts to saturate as the kernel size continues growing, compared to the scaling trend of advanced ViTs such as Swin Transformer. In this paper, we explore the possibility of training extreme convolutions larger than 31x31 and test whether the performance gap can be eliminated by strategically enlarging convolutions. This study ends up with a recipe for applying extremely large kernels from the perspective of sparsity, which can smoothly scale up kernels to 61x61 with better performance. Built on this recipe, we propose Sparse Large Kernel Network (SLaK), a pure CNN architecture equipped with sparse factorized 51x51 kernels that can perform on par with or better than state-of-the-art hierarchical Transformers and modern ConvNet architectures like ConvNeXt and RepLKNet, on ImageNet classification as well as a wide range of downstream tasks including semantic segmentation on ADE20K, object detection on PASCAL VOC 2007, and object detection/segmentation on MS COCO.

Joakim Linja, Joonas Hämäläinen, Antti Pihlajamäki et al.

Molecular-level understanding of the interactions between the constituents of an atomic structure is essential for designing novel materials in various applications. This need goes beyond the basic knowledge of the number and types of atoms, their chemical composition, and the character of the chemical interactions. The bigger picture takes place on the quantum level which can be addressed by using the Density-functional theory (DFT). Use of DFT, however, is a computationally taxing process, and its results do not readily provide easily interpretable insight into the atomic interactions which would be useful information in material design. An alternative way to address atomic interactions is to use an interpretable machine learning approach, where a predictive DFT surrogate is constructed and analyzed. The purpose of this paper is to propose such a procedure using a modification of the recently published interpretable distance-based regression method. Our tests with a representative benchmark set of molecules and a complex hybrid nanoparticle confirm the viability and usefulness of the proposed approach.

Tommi Kärkkäinen, Jan Hänninen

An additive autoencoder for dimension reduction, which is composed of a serially performed bias estimation, linear trend estimation, and nonlinear residual estimation, is proposed and analyzed. Computational experiments confirm that an autoencoder of this form, with only a shallow network to encapsulate the nonlinear behavior, is able to identify an intrinsic dimension of a dataset with a low autoencoding error. This observation leads to an investigation in which shallow and deep network structures, and how they are trained, are compared. We conclude that the deeper network structures obtain lower autoencoding errors during the identification of the intrinsic dimension. However, the detected dimension does not change compared to a shallow network.

Danial Hooshyar, Yeongwook Yang, Gustav Šíř et al.

The rapid rise of large language model (LLM)-based tutors in K--12 education has fostered a misconception that generative models can replace traditional learner modelling for adaptive instruction. This is especially problematic in K--12 settings, which the EU AI Act classifies as high-risk domain requiring responsible design. Motivated by these concerns, this study synthesises evidence on limitations of LLM-based tutors and empirically investigates one critical issue: the accuracy, reliability, and temporal coherence of assessing learners' evolving knowledge over time. We compare a deep knowledge tracing (DKT) model with a widely used LLM, evaluated zero-shot and fine-tuned, using a large open-access dataset. Results show that DKT achieves the highest discrimination performance (AUC = 0.83) on next-step correctness prediction and consistently outperforms the LLM across settings. Although fine-tuning improves the LLM's AUC by approximately 8\% over the zero-shot baseline, it remains 6\% below DKT and produces higher early-sequence errors, where incorrect predictions are most harmful for adaptive support. Temporal analyses further reveal that DKT maintains stable, directionally correct mastery updates, whereas LLM variants exhibit substantial temporal weaknesses, including inconsistent and wrong-direction updates. These limitations persist despite the fine-tuned LLM requiring nearly 198 hours of high-compute training, far exceeding the computational demands of DKT. Our qualitative analysis of multi-skill mastery estimation further shows that, even after fine-tuning, the LLM produced inconsistent mastery trajectories, while DKT maintained smooth and coherent updates. Overall, the findings suggest that LLMs alone are unlikely to match the effectiveness of established intelligent tutoring systems, and that responsible tutoring requires hybrid frameworks that incorporate learner modelling.

Haihua Luo, Xuming Ran, Tommi Kärkkäinen et al.

The dynamic evolution of real-world necessitates model editing within Large Language Models. While existing methods explore modular isolation or parameter-efficient strategies, they still suffer from semantic drift or knowledge forgetting due to continual updating. To address these challenges, we propose SoLA, a Semantic routing-based LoRA framework for lifelong model editing. In SoLA, each edit is encapsulated as an independent LoRA module, which is frozen after training and mapped to input by semantic routing, allowing dynamic activation of LoRA modules via semantic matching. This mechanism avoids semantic drift caused by cluster updating and mitigates catastrophic forgetting from parameter sharing. More importantly, SoLA supports precise revocation of specific edits by removing key from semantic routing, which restores model's original behavior. To our knowledge, this reversible rollback editing capability is the first to be achieved in existing literature. Furthermore, SoLA integrates decision-making process into edited layer, eliminating the need for auxiliary routing networks and enabling end-to-end decision-making process. Extensive experiments demonstrate that SoLA effectively learns and retains edited knowledge, achieving accurate, efficient, and reversible lifelong model editing.

Haihua Luo, Xuming Ran, Zhengji Li et al.

Continual learning aims to enable models to acquire new knowledge while retaining previously learned information. Prompt-based methods have shown remarkable performance in this domain; however, they typically rely on key-value pairing, which can introduce inter-task interference and hinder scalability. To overcome these limitations, we propose a novel approach employing task-specific Prompt-Prototype (ProP), thereby eliminating the need for key-value pairs. In our method, task-specific prompts facilitate more effective feature learning for the current task, while corresponding prototypes capture the representative features of the input. During inference, predictions are generated by binding each task-specific prompt with its associated prototype. Additionally, we introduce regularization constraints during prompt initialization to penalize excessively large values, thereby enhancing stability. Experiments on several widely used datasets demonstrate the effectiveness of the proposed method. In contrast to mainstream prompt-based approaches, our framework removes the dependency on key-value pairs, offering a fresh perspective for future continual learning research.

Haihua Luo, Xuming Ran, Tommi Kärkkäinen et al.

The world is inherently dynamic, and continual learning aims to enable models to adapt to ever-evolving data streams. While pre-trained models have shown powerful performance in continual learning, they still require finetuning to adapt effectively to downstream tasks. However, prevailing Parameter-Efficient Fine-Tuning (PEFT) methods operate through empirical, black-box optimization at the weight level. These approaches lack explicit control over representation drift, leading to sensitivity to domain shifts and catastrophic forgetting in continual learning scenarios. In this work, we introduce Continual Representation Learning (CoRe), a novel framework that for the first time shifts the finetuning paradigm from weight space to representation space. Unlike conventional methods, CoRe performs task-specific interventions within a low-rank linear subspace of hidden representations, adopting a learning process with explicit objectives, which ensures stability for past tasks while maintaining plasticity for new ones. By constraining updates to a low-rank subspace, CoRe achieves exceptional parameter efficiency. Extensive experiments across multiple continual learning benchmarks demonstrate that CoRe not only preserves parameter efficiency but also significantly outperforms existing state-of-the-art methods. Our work introduces representation finetuning as a new, more effective and interpretable paradigm for continual learning.

Mika Setälä, Ville Heilala, Pieta Sikström et al.

This study investigated the students' perceptions of using Generative Artificial Intelligence (GenAI) in upper-secondary mathematics education. Data was collected from Finnish high school students to represent how key constructs of the Technology Acceptance Model (Perceived Usefulness, Perceived Ease of Use, Perceived Enjoyment, and Intention to Use) influence the adoption of AI tools. First, a structural equation model for a comparative study with a prior study was constructed and analyzed. Then, an extended model with the additional construct of Compatibility, which represents the alignment of AI tools with students' educational experiences and needs, was proposed and analyzed. The results demonstrated a strong influence of perceived usefulness on the intention to use GenAI, emphasizing the statistically significant role of perceived enjoyment in determining perceived usefulness and ease of use. The inclusion of compatibility improved the model's explanatory power, particularly in predicting perceived usefulness. This study contributes to a deeper understanding of how AI tools can be integrated into mathematics education and highlights key differences between the Finnish educational context and previous studies based on structural equation modeling.

Danial Hooshyar, Gustav Šír, Yeongwook Yang et al.

Despite significant advancements in AI-driven educational systems and ongoing calls for responsible AI for education, several critical issues remain unresolved -- acting as the elephant in the room within AI in education, learning analytics, educational data mining, learning sciences, and educational psychology communities. This critical analysis identifies and examines nine persistent challenges that continue to undermine the fairness, transparency, and effectiveness of current AI methods and applications in education. These include: (1) the lack of clarity around what AI for education truly means -- often ignoring the distinct purposes, strengths, and limitations of different AI families -- and the trend of equating it with domain-agnostic, company-driven large language models; (2) the widespread neglect of essential learning processes such as motivation, emotion, and (meta)cognition in AI-driven learner modelling and their contextual nature; (3) limited integration of domain knowledge and lack of stakeholder involvement in AI design and development; (4) continued use of non-sequential machine learning models on temporal educational data; (5) misuse of non-sequential metrics to evaluate sequential models; (6) use of unreliable explainable AI methods to provide explanations for black-box models; (7) ignoring ethical guidelines in addressing data inconsistencies during model training; (8) use of mainstream AI methods for pattern discovery and learning analytics without systematic benchmarking; and (9) overemphasis on global prescriptions while overlooking localised, student-specific recommendations. Supported by theoretical and empirical research, we demonstrate how hybrid AI methods -- specifically neural-symbolic AI -- can address the elephant in the room and serve as the foundation for responsible, trustworthy AI systems in education.

Mika Setälä, Pieta Sikström, Ville Heilala et al.

Large language models (LLMs) have shown increasing promise in educational settings, yet their mathematical reasoning has been considered evolving. This study evaluates the mathematical capabilities of various LLMs using the Finnish matriculation examination, a high-stakes digital test for upper secondary education. Initial tests yielded moderate performance corresponding to mid-range grades, but later evaluations demonstrated substantial improvements as the language models evolved. Remarkably, some models achieved near-perfect or perfect scores, matching top student performance and qualifying for university admission. Our findings highlight the rapid advances in the mathematical proficiency of LLMs and illustrate their potential as underlying tools to support learning and teaching in a variety of ways.

Danial Hooshyar, Eve Kikas, Yeongwook Yang et al.

Given the demand for responsible and trustworthy AI for education, this study evaluates symbolic, sub-symbolic, and neural-symbolic AI (NSAI) in terms of generalizability and interpretability. Our extensive experiments on balanced and imbalanced self-regulated learning datasets of Estonian primary school students predicting 7th-grade mathematics national test performance showed that symbolic and sub-symbolic methods performed well on balanced data but struggled to identify low performers in imbalanced datasets. Interestingly, symbolic and sub-symbolic methods emphasized different factors in their decision-making: symbolic approaches primarily relied on cognitive and motivational factors, while sub-symbolic methods focused more on cognitive aspects, learnt knowledge, and the demographic variable of gender -- yet both largely overlooked metacognitive factors. The NSAI method, on the other hand, showed advantages by: (i) being more generalizable across both classes -- even in imbalanced datasets -- as its symbolic knowledge component compensated for the underrepresented class; and (ii) relying on a more integrated set of factors in its decision-making, including motivation, (meta)cognition, and learnt knowledge, thus offering a comprehensive and theoretically grounded interpretability framework. These contrasting findings highlight the need for a holistic comparison of AI methods before drawing conclusions based solely on predictive performance. They also underscore the potential of hybrid, human-centred NSAI methods to address the limitations of other AI families and move us closer to responsible AI for education. Specifically, by enabling stakeholders to contribute to AI design, NSAI aligns learned patterns with theoretical constructs, incorporates factors like motivation and metacognition, and strengthens the trustworthiness and responsibility of educational data mining.

Marko Niemelä, Mikaela von Bonsdorff, Sami Äyrämö et al.

Memory disorders are a central factor in the decline of functioning and daily activities in elderly individuals. The confirmation of the illness, initiation of medication to slow its progression, and the commencement of occupational therapy aimed at maintaining and rehabilitating cognitive abilities require a medical diagnosis. The early identification of symptoms of memory disorders, especially the decline in cognitive abilities, plays a significant role in ensuring the well-being of populations. Features related to speech production are known to connect with the speaker's cognitive ability and changes. The lack of standardized speech tests in clinical settings has led to a growing emphasis on developing automatic machine learning techniques for analyzing naturally spoken language. Non-lexical but acoustic properties of spoken language have proven useful when fast, cost-effective, and scalable solutions are needed for the rapid diagnosis of a disease. The work presents an approach related to feature selection, allowing for the automatic selection of the essential features required for diagnosis from the Geneva minimalistic acoustic parameter set and relative speech pauses, intended for automatic paralinguistic and clinical speech analysis. These features are refined into word histogram features, in which machine learning classifiers are trained to classify control subjects and dementia patients from the Dementia Bank's Pitt audio database. The results show that achieving a 75% average classification accuracy with only twenty-five features with the separate ADReSS 2020 competition test data and the Leave-One-Subject-Out cross-validation of the entire competition data is possible. The results rank at the top compared to international research, where the same dataset and only acoustic features have been used to diagnose patients.

Marko Niemelä, Mikaela von Bonsdorff, Sami Äyrämö et al.

Dementia is a general term for a group of syndromes that affect cognitive functions such as memory, thinking, reasoning, and the ability to perform daily tasks. The number of dementia patients is increasing as the population ages, and it is estimated that over 10 million people develop dementia each year. Dementia progresses gradually, and the sooner a patient receives help and support, the better their chances of maintaining their functional abilities. For this reason, early diagnosis of dementia is important. In recent years, machine learning models based on naturally spoken language have been developed for the early diagnosis of dementia. These methods have proven to be user-friendly, cost-effective, scalable, and capable of providing extremely fast diagnoses. This study utilizes the well-known ADReSS challenge dataset for classifying healthy controls and Alzheimer's patients. The dataset contains speech recordings from a picture description task featuring a kitchen scene, collected from both healthy controls and dementia patients. Unlike most studies, this research does not segment the audio recordings into active speech segments; instead, acoustic features are extracted from entire recordings. The study employs Ridge linear regression, Extreme Minimal Learning Machine, and Linear Support Vector Machine machine learning models to compute feature importance scores based on model outputs. The Ridge model performed best in Leave-One-Subject-Out cross-validation, achieving a classification accuracy of 87.8%. The EMLM model, proved to be effective in both cross-validation and the classification of a separate test dataset, with accuracies of 85.3% and 79.2%, respectively. The study's results rank among the top compared to other studies using the same dataset and acoustic feature extraction for dementia diagnosis.

Ville Heilala, Sami Lehesvuori, Raija Hämäläinen et al.

This study employed multimodal learning analytics (MMLA) to analyze behavioral dynamics during the ABCDE procedure in nursing education, focusing on gaze entropy, hand movement velocities, and proximity measures. Utilizing accelerometers and eye-tracking techniques, behaviorgrams were generated to depict various procedural phases. Results identified four primary phases characterized by distinct patterns of visual attention, hand movements, and proximity to the patient or instruments. The findings suggest that MMLA can offer valuable insights into procedural competence in medical education. This research underscores the potential of MMLA to provide detailed, objective evaluations of clinical procedures and their inherent complexities.

Joonas Hämäläinen, Antoine Hubermont, Amauri Souza et al.

Distance-based supervised method, the minimal learning machine, constructs a predictive model from data by learning a mapping between input and output distance matrices. In this paper, we propose new methods and evaluate how their core component, the distance mapping, can be adapted to multi-label learning. The proposed approach is based on combining the distance mapping with an inverse distance weighting. Although the proposal is one of the simplest methods in the multi-label learning literature, it achieves state-of-the-art performance for small to moderate-sized multi-label learning problems. In addition to its simplicity, the proposed method is fully deterministic: Its hyper-parameter can be selected via ranking loss-based statistic which has a closed form, thus avoiding conventional cross-validation-based hyper-parameter tuning. In addition, due to its simple linear distance mapping-based construction, we demonstrate that the proposed method can assess the uncertainty of the predictions for multi-label classification, which is a valuable capability for data-centric machine learning pipelines.

Joonas Hämäläinen, Tommi Kärkkäinen, Tuomo Rossi

In this work, two new initialization methods for K-means clustering are proposed. Both proposals are based on applying a divide-and-conquer approach for the K-means|| type of an initialization strategy. The second proposal also utilizes multiple lower-dimensional subspaces produced by the random projection method for the initialization. The proposed methods are scalable and can be run in parallel, which make them suitable for initializing large-scale problems. In the experiments, comparison of the proposed methods to the K-means++ and K-means|| methods is conducted using an extensive set of reference and synthetic large-scale datasets. Concerning the latter, a novel high-dimensional clustering data generation algorithm is given. The experiments show that the proposed methods compare favorably to the state-of-the-art. We also observe that the currently most popular K-means++ initialization behaves like the random one in the very high-dimensional cases.

Anton Akusok, Mirka Saarela, Tommi Kärkkäinen et al.

The paper proposes to analyze a data set of Finnish ranks of academic publication channels with Extreme Learning Machine (ELM). The purpose is to introduce and test recently proposed ELM-based mislabel detection approach with a rich set of features characterizing a publication channel. We will compare the architecture, accuracy, and, especially, the set of detected mislabels of the ELM-based approach to the corresponding reference results on the reference paper.

Jarno Kansanaho, Tommi Kärkkäinen

Increasing the capabilities of sensors and computer algorithms produces a need for structural support that would solve recurring problems. Autonomous tribotronic systems self-regulate based on feedback acquired from interacting surfaces in relative motion. This paper describes a software framework for tribotronic systems. An example of such an application is a rolling element bearing (REB) installation with a vibration sensor. The presented plug-in framework offers functionalities for vibration data management, feature extraction, fault detection, and remaining useful life (RUL) estimation. The framework was tested using bearing vibration data acquired from NASA's prognostics data repository, and the evaluation included a run-through from feature extraction to fault detection to remaining useful life estimation. The plug-in implementations are easy to update and new implementations are easily deployable, even in run-time. The proposed software framework improves the performance, efficiency, and reliability of a tribotronic system. In addition, the framework facilitates the evaluation of the configuration complexity of the plug-in implementation.

Joonas Hämäläinen, Alisson S. C. Alencar, Tommi Kärkkäinen et al.

The Minimal Learning Machine (MLM) is a nonlinear supervised approach based on learning a linear mapping between distance matrices computed in the input and output data spaces, where distances are calculated using a subset of points called reference points. Its simple formulation has attracted several recent works on extensions and applications. In this paper, we aim to address some open questions related to the MLM. First, we detail theoretical aspects that assure the interpolation and universal approximation capabilities of the MLM, which were previously only empirically verified. Second, we identify the task of selecting reference points as having major importance for the MLM's generalization capability. Several clustering-based methods for reference point selection in regression scenarios are then proposed and analyzed. Based on an extensive empirical evaluation, we conclude that the evaluated methods are both scalable and useful. Specifically, for a small number of reference points, the clustering-based methods outperformed the standard random selection of the original MLM formulation.