User profiles for L. Schietgat
Leander SchietgatResearch & Innovation Manager, Artificial Intelligence Lab, VUB Verified email at vub.be Cited by 1835 |
Decision trees for hierarchical multi-label classification
… Schietgat · H. Blockeel Department of Computer Science, Katholieke Universiteit Leuven, …
Leander Schietgat is supported by a PhD grant of the Institute for the Promotion of Innovation …
Leander Schietgat is supported by a PhD grant of the Institute for the Promotion of Innovation …
Predicting human olfactory perception from chemical features of odor molecules
It is still not possible to predict whether a given molecule will have a perceived odor or what
olfactory percept it will produce. We therefore organized the crowd-sourced DREAM …
olfactory percept it will produce. We therefore organized the crowd-sourced DREAM …
[HTML][HTML] Predicting gene function using hierarchical multi-label decision tree ensembles
Background S. cerevisiae, A. thaliana and M. musculus are well-studied organisms in biology
and the sequencing of their genomes was completed many years ago. It is still a challenge…
and the sequencing of their genomes was completed many years ago. It is still a challenge…
Decision trees for hierarchical multilabel classification: A case study in functional genomics
… , 3001 Leuven, Belgium {hendrik.blockeel, leander.schietgat, jan.struyf}@cs.kuleuven.be 2
Dept… Torgo, L.: A comparative study of reliable error estimators for pruning regression trees. In …
Dept… Torgo, L.: A comparative study of reliable error estimators for pruning regression trees. In …
Predicting tryptic cleavage from proteomics data using decision tree ensembles
Trypsin is the workhorse protease in mass spectrometry-based proteomics experiments and
is used to digest proteins into more readily analyzable peptides. To identify these peptides …
is used to digest proteins into more readily analyzable peptides. To identify these peptides …
[HTML][HTML] A machine learning based framework to identify and classify long terminal repeat retrotransposons
… Third, in contrast to classification methods such as LtrDigest, LtrSift, RepClass, Pastec and
LtrClassifier, our method is not based on a predefined set of rules. Instead, we exploit the …
LtrClassifier, our method is not based on a predefined set of rules. Instead, we exploit the …
On the complexity of haplotyping a microbial community
… Similarly, a pair of SNPs s k , s l are said to be in SNP conflict if reads r u and r v are …
We define L as the ‘lookback’ size, the number of variants of the current path to consider …
We define L as the ‘lookback’ size, the number of variants of the current path to consider …
Beyond global and local multi-target learning
In multi-target prediction, an instance has to be classified along multiple target variables at the
same time, where each target represents a category or numerical value. There are several …
same time, where each target represents a category or numerical value. There are several …
A Q-Learning algorithm for flexible job shop scheduling in a real-world manufacturing scenario
JC Palacio, YM Jiménez, L Schietgat, B Van Doninck… - Procedia CIRP, 2022 - Elsevier
In this work we propose a Reinforcement Learning approach for a real-world flexible job
shop scheduling scenario, where a two-armed robot and a human operator share two …
shop scheduling scenario, where a two-armed robot and a human operator share two …
Effective feature construction by maximum common subgraph sampling
The standard approach to feature construction and predictive learning in molecular datasets
is to employ computationally expensive graph mining techniques and to bias the feature …
is to employ computationally expensive graph mining techniques and to bias the feature …