59 citations · 238 across the 27 of their papers we have counts for
27 papers
Njord: A Probabilistic Graph Neural Network for Ensemble Ocean Forecasting
Daniel Holmberg, Joel Oskarsson, Erik Wikingsson +2
Ocean dynamics are inherently chaotic, yet existing machine learning ocean models produce only deterministic forecasts. We introduce Njord, a probabilistic data-driven model for oc…
LEMUR: Learned Multi-Vector Retrieval
Elias Jääsaari, Ville Hyvönen, Teemu Roos
Multi-vector representations generated by late interaction models, such as ColBERT, enable superior retrieval quality compared to single-vector representations in information retri…
Deterministic and probabilistic neural surrogates of global hybrid-Vlasov simulations
Daniel Holmberg, Ivan Zaitsev, Markku Alho +5
Hybrid-Vlasov simulations resolve ion-kinetic effects in the solar wind-magnetosphere interaction, but even 5D (2D + 3V) configurations are computationally expensive. We show that…
Graph-based Neural Space Weather Forecasting
Daniel Holmberg, Ivan Zaitsev, Markku Alho +5
Accurate space weather forecasting is crucial for protecting our increasingly digital infrastructure. Hybrid-Vlasov models, like Vlasiator, offer physical realism beyond that of cu…
Breakable Machine: A K-12 Classroom Game for Transformative AI Literacy Through Spoofing and eXplainable AI (XAI)
Olli Hilke, Nicolas Pope, Juho Kahila +4
This paper, submitted to the special track on resources for teaching AI in K-12, presents an eXplainable AI (XAI)-based classroom game "Breakable Machine" for teaching critical, tr…
Accurate Mediterranean Sea forecasting via graph-based deep learning
Daniel Holmberg, Emanuela Clementi, Italo Epicoco +1
Accurate ocean forecasting systems are essential for understanding marine dynamics, which play a crucial role in sectors such as shipping, aquaculture, environmental monitoring, an…
VIBE: Vector Index Benchmark for Embeddings
Elias Jääsaari, Ville Hyvönen, Matteo Ceccarello +2
Approximate nearest neighbor (ANN) search is a performance-critical component of many machine learning pipelines, and rigorous benchmarking is essential for assessing the performan…
An XAI Social Media Platform for Teaching K-12 Students AI-Driven Profiling, Clustering, and Engagement-Based Recommending
Nicolas Pope, Juho Kahila, Henriikka Vartiainen +5
This paper, submitted to the special track on resources for teaching AI in K-12, presents an explainable AI (XAI) education tool designed for K-12 classrooms, particularly for stud…
Regional Ocean Forecasting with Hierarchical Graph Neural Networks
Daniel Holmberg, Emanuela Clementi, Teemu Roos
Accurate ocean forecasting systems are vital for understanding marine dynamics, which play a crucial role in environmental management and climate adaptation strategies. Traditional…
LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search
Elias Jääsaari, Ville Hyvönen, Teemu Roos
Approximate nearest neighbor (ANN) search is a key component in many modern machine learning pipelines; recent use cases include retrieval-augmented generation (RAG) and vector dat…
Quotient Normalized Maximum Likelihood Criterion for Learning Bayesian Network Structures
Tomi Silander, Janne Leppä-aho, Elias Jääsaari +1
We introduce an information theoretic criterion for Bayesian network structure learning which we call quotient normalized maximum likelihood (qNML). In contrast to the closely rela…
An Educational Tool for Learning about Social Media Tracking, Profiling, and Recommendation
Nicolas Pope, Juho Kahila, Jari Laru +3
This paper introduces an educational tool for classroom use, based on explainable AI (XAI), designed to demystify key social media mechanisms - tracking, profiling, and content rec…
Learning Developmental Age from 3D Infant Kinetics Using Adaptive Graph Neural Networks
Daniel Holmberg, Manu Airaksinen, Viviana Marchi +5
Reliable methods for the neurodevelopmental assessment of infants are essential for early detection of problems that may need prompt interventions. Spontaneous motor activity, or '…
Graph Representation of the Magnetic Field Topology in High-Fidelity Plasma Simulations for Machine Learning Applications
Ioanna Bouri, Fanni Franssila, Markku Alho +4
Topological analysis of the magnetic field in simulated plasmas allows the study of various physical phenomena in a wide range of settings. One such application is magnetic reconne…
Transfer Learning with Ensembles of Deep Neural Networks for Skin Cancer Detection in Imbalanced Data Sets
Aqsa Saeed Qureshi, Teemu Roos
Several machine learning techniques for accurate detection of skin cancer from medical images have been reported. Many of these techniques are based on pre-trained convolutional ne…
Gradient-Based Training and Pruning of Radial Basis Function Networks with an Application in Materials Physics
Jussi Määttä, Viacheslav Bazaliy, Jyri Kimari +3
Many applications, especially in physics and other sciences, call for easily interpretable and robust machine learning techniques. We propose a fully gradient-based technique for t…
A Multilabel Classification Framework for Approximate Nearest Neighbor Search
Ville Hyvönen, Elias Jääsaari, Teemu Roos
Both supervised and unsupervised machine learning algorithms have been used to learn partition-based index structures for approximate nearest neighbor (ANN) search. Existing superv…
Minimum Description Length Revisited
Peter Grünwald, Teemu Roos
This is an up-to-date introduction to and overview of the Minimum Description Length (MDL) Principle, a theory of inductive inference that can be applied to general problems in sta…
Efficient Autotuning of Hyperparameters in Approximate Nearest Neighbor Search
Elias Jääsaari, Ville Hyvönen, Teemu Roos
Approximate nearest neighbor algorithms are used to speed up nearest neighbor search in a wide array of applications. However, current indexing methods feature several hyperparamet…
An Application of Storage-Optimal MatDot Codes for Coded Matrix Multiplication: Fast k-Nearest Neighbors Estimation
Utsav Sheth, Sanghamitra Dutta, Malhar Chaudhari +5
We propose a novel application of coded computing to the problem of the nearest neighbor estimation using MatDot Codes [Fahim. et.al. 2017], that are known to be optimal for matrix…
Learning non-parametric Markov networks with mutual information
Janne Leppä-aho, Santeri Räisänen, Xiao Yang +1
We propose a method for learning Markov network structures for continuous data without invoking any assumptions about the distribution of the variables. The method makes use of pre…
Learning Gaussian Graphical Models With Fractional Marginal Pseudo-likelihood
Janne Leppä-aho, Johan Pensar, Teemu Roos +1
We propose a Bayesian approximate inference method for learning the dependence structure of a Gaussian graphical model. Using pseudo-likelihood, we derive an analytical expression…
Fast k-NN search
Ville Hyvönen, Teemu Pitkänen, Sotiris Tasoulis +5
Efficient index structures for fast approximate nearest neighbor queries are required in many applications such as recommendation systems. In high-dimensional spaces, many conventi…
Bayesian Properties of Normalized Maximum Likelihood and its Fast Computation
Andrew Barron, Teemu Roos, Kazuho Watanabe
The normalized maximized likelihood (NML) provides the minimax regret solution in universal data compression, gambling, and prediction, and it plays an essential role in the minimu…