no code implementations • 29 Apr 2024 • Stefan F. Schouten, Peter Bloem, Ilia Markov, Piek Vossen
Recent work has demonstrated that the latent spaces of large language models (LLMs) contain directions predictive of the truth of sentences.
1 code implementation • 23 Oct 2023 • Stefan F. Schouten, Peter Bloem, Ilia Markov, Piek Vossen
But no resources exist to evaluate how well Large Language Models can use explicit reasoning to resolve ambiguity in language.
1 code implementation • 5 Oct 2023 • Taraneh Younesian, Thiviyan Thanapalasingam, Emile van Krieken, Daniel Daza, Peter Bloem
Graph neural networks (GNNs) learn the representation of nodes in a graph by aggregating the neighborhood information in various ways.
1 code implementation • 13 Jul 2023 • Thiviyan Thanapalasingam, Emile van Krieken, Peter Bloem, Paul Groth
However, Knowledge Graphs are not just sets of links but also have semantics underlying their structure.
1 code implementation • 21 Jul 2021 • Thiviyan Thanapalasingam, Lucas van Berkel, Peter Bloem, Paul Groth
In this paper, we describe a reproduction of the Relational Graph Convolutional Network (RGCN).
1 code implementation • 16 Apr 2021 • Peter Bloem
We introduce a method to find network motifs in knowledge graphs.
no code implementations • 9 Dec 2020 • Tijs Maas, Peter Bloem
Many traffic prediction applications rely on uncertainty estimates instead of the mean prediction.
no code implementations • 14 Feb 2020 • Ahmed El-Gazzar, Mirjam Quaak, Leonardo Cerliani, Peter Bloem, Guido van Wingen, Rajat Mani Thomas
Functional Magnetic Resonance Imaging (fMRI) captures the temporal dynamics of neural activity as a function of spatial location in the brain.
1 code implementation • 29 Aug 2019 • Radu Sibechi, Olaf Booij, Nora Baka, Peter Bloem
In this paper, we tackle the issue of label scarcity by using consecutive frames of a video, where only one frame is annotated.
1 code implementation • 14 Aug 2019 • Floris Hermsen, Peter Bloem, Fabian Jansen, Wolf Vos
We study the problem of end-to-end learning from complex multigraphs with potentially very large numbers of edges between two vertices, each edge labeled with rich information.
no code implementations • 7 Dec 2018 • Koen Lennart van der Veen, Ruben Seggers, Peter Bloem, Giorgio Patrini
Differentially private learning on real-world data poses challenges for standard machine learning practice: privacy guarantees are difficult to interpret, hyperparameter tuning on private data reduces the privacy budget, and ad-hoc privacy attacks are often required to test model privacy.
no code implementations • 31 Oct 2018 • Peter Bloem, Steven de Rooij
This document provides a tutorial description of the use of the MDL principle in complex graph analysis.
2 code implementations • 22 Oct 2018 • Peter Bloem
Many transformations in deep learning architectures are sparsely connected.
1 code implementation • 11 Jun 2018 • Rein van 't Veer, Peter Bloem, Erwin Folmer
In this paper, we evaluate the accuracy of deep learning approaches on geospatial vector geometry classification tasks.
1 code implementation • 9 Jun 2017 • Peter Bloem, Steven de Rooij
We present an Expectation-Maximization algorithm for the fractal inverse problem: the problem of fitting a fractal model to data.
27 code implementations • 17 Mar 2017 • Michael Schlichtkrull, Thomas N. Kipf, Peter Bloem, Rianne van den Berg, Ivan Titov, Max Welling
We demonstrate the effectiveness of R-GCNs as a stand-alone model for entity classification.
Ranked #1 on Node Classification on AIFB
no code implementations • 8 Jan 2017 • Peter Bloem, Steven de Rooij
We introduce a new method for finding network motifs: interesting or informative subgraph patterns in a network.