activity
20202022
most citedParameterless Gene-pool Optimal Mixing Evolutionary Algorithms

4 citations · 7 across the 6 of their papers we have counts for

collaborators

7 papers

eess.IV2022

Data variation-aware medical image segmentation

Arkadiy Dushatskiy, Gerry Lowe, Peter A. N. Bosman +1

Deep learning algorithms have become the golden standard for segmentation of medical imaging data. In most works, the variability and heterogeneity of real clinical data is acknowl…

eess.IV2022

Mixed-Block Neural Architecture Search for Medical Image Segmentation

Martijn M. A. Bosma, Arkadiy Dushatskiy, Monika Grewal +2

Deep Neural Networks (DNNs) have the potential for making various clinical procedures more time-efficient by automating medical image segmentation. Due to their strong, in some cas…

cs.NE20223 cited

Heed the Noise in Performance Evaluations in Neural Architecture Search

Arkadiy Dushatskiy, Tanja Alderliesten, Peter A. N. Bosman

Neural Architecture Search (NAS) has recently become a topic of great interest. However, there is a potentially impactful issue within NAS that remains largely unrecognized: noise.…

cs.NE20214 cited

Parameterless Gene-pool Optimal Mixing Evolutionary Algorithms

Arkadiy Dushatskiy, Marco Virgolin, Anton Bouter +2

When it comes to solving optimization problems with evolutionary algorithms (EAs) in a reliable and scalable manner, detecting and exploiting linkage information, i.e., dependencie…

cs.NE2021

A Novel Surrogate-assisted Evolutionary Algorithm Applied to Partition-based Ensemble Learning

Arkadiy Dushatskiy, Tanja Alderliesten, Peter A. N. Bosman

We propose a novel surrogate-assisted Evolutionary Algorithm for solving expensive combinatorial optimization problems. We integrate a surrogate model, which is used for fitness va…

cs.NE2020

Local Search is a Remarkably Strong Baseline for Neural Architecture Search

T. Den Ottelander, A. Dushatskiy, M. Virgolin +1

Neural Architecture Search (NAS), i.e., the automation of neural network design, has gained much popularity in recent years with increasingly complex search algorithms being propos…