no code implementations • 6 Sep 2023 • David Novak, Sofie Van Gassen, Yvan Saeys
Recent advances in dimensionality reduction have achieved more accurate lower-dimensional embeddings of high-dimensional data.
1 code implementation • 9 Jan 2023 • Edith Heiter, Robin Vandaele, Tijl De Bie, Yvan Saeys, Jefrey Lijffijt
In some cases, users may have prior topological knowledge about the data, such as a known cluster structure or the fact that the data is known to lie along a tree- or graph-structured topology.
no code implementations • 7 Sep 2022 • Arne Gevaert, Jonathan Peck, Yvan Saeys
In this work, we present an algorithm to distill the policy from a deep Q-network into a compact neuro-fuzzy controller.
no code implementations • 26 Aug 2022 • Arne Gevaert, Yvan Saeys
Because of their strong theoretical properties, Shapley values have become very popular as a way to explain predictions made by black box models.
1 code implementation • 22 Feb 2022 • Arne Gevaert, Axel-Jan Rousseau, Thijs Becker, Dirk Valkenborg, Tijl De Bie, Yvan Saeys
Feature attribution maps are a popular approach to highlight the most important pixels in an image for a given prediction of a model.
1 code implementation • ICLR 2022 • Robin Vandaele, Bo Kang, Jefrey Lijffijt, Tijl De Bie, Yvan Saeys
For tasks for which prior expert topological knowledge is available, incorporating this into the learned representation may lead to higher quality embeddings.
1 code implementation • 22 Sep 2021 • Robin Vandaele, Bo Kang, Tijl De Bie, Yvan Saeys
Previously, it has been argued that neighborhood queries become meaningless and unstable when distance concentration occurs, which means that there is a poor relative discrimination between the furthest and closest neighbors in the data.
1 code implementation • 7 Jul 2020 • Utku Ozbulak, Jonathan Peck, Wesley De Neve, Bart Goossens, Yvan Saeys, Arnout Van Messem
Regional adversarial attacks often rely on complicated methods for generating adversarial perturbations, making it hard to compare their efficacy against well-known attacks.
no code implementations • 13 Nov 2019 • Joris Roels, Yvan Saeys
Our experiments on three different electron microscopy datasets show that active learning can improve segmentation quality by 10 to 15% in terms of Jaccard score compared to standard randomized sampling.
1 code implementation • 3 Dec 2018 • Lukas M. Weber, Wouter Saelens, Robrecht Cannoodt, Charlotte Soneson, Alexander Hapfelmeier, Paul Gardner, Anne-Laure Boulesteix, Yvan Saeys, Mark D. Robinson
In computational biology and other sciences, researchers are frequently faced with a choice between several computational methods for performing data analyses.
1 code implementation • 23 Oct 2018 • Joris Roels, Julian Hennies, Yvan Saeys, Wilfried Philips, Anna Kreshuk
In this work, we extend recently proposed classification DA techniques to an encoder-decoder layout and propose a novel method that adds a reconstruction decoder to the classical encoder-decoder segmentation in order to align source and target encoder features.
no code implementations • 23 Oct 2018 • Joris Roels, Jonas De Vylder, Jan Aelterman, Yvan Saeys, Wilfried Philips
Biological membranes are one of the most basic structures and regions of interest in cell biology.
no code implementations • 23 Oct 2018 • Joris Roels, Jan Aelterman, Jonas De Vylder, Hiep Luong, Yvan Saeys, Wilfried Philips
Microscopy is one of the most essential imaging techniques in life sciences.
no code implementations • NeurIPS 2017 • Jonathan Peck, Joris Roels, Bart Goossens, Yvan Saeys
The input-output mappings learned by state-of-the-art neural networks are significantly discontinuous.
no code implementations • 27 Nov 2017 • Jasper Zuallaert, Mijung Kim, Yvan Saeys, Wesley De Neve
Thanks to rapidly evolving sequencing techniques, the amount of genomic data at our disposal is growing increasingly large.
no code implementations • 21 Mar 2017 • Daniel Peralta, Isaac Triguero, Salvador García, Yvan Saeys, Jose M. Benitez, Francisco Herrera
In our experiments, convolutional neural networks yielded better accuracy and penetration rate than state-of-the-art classifiers based on explicit feature extraction.