Leiden University Scholarly Publications

Critically assessing the state of the art in neural network verification

Accelerating adversarially robust model selection for deep neural networks via racing

The bigger fish

Critically assessing the state of the art in CPU-based local robustness verification

Speeding up neural network robustness verification via algorithm configuration and an optimised mixed integer linear programming solver portfolio

Hyperparameter importance of quantum neural networks across small datasets

Automated machine learning for satellite data

Speeding up neural network verification via automated algorithm configuration

Learning multiple defaults for machine learning algorithms

Meta-learning for symbolic hyperparameter defaults

Towards model selection using learning curve cross-validation

Advances in MetaDL: AAAI 2021 Challenge and Workshop

Towards algorithm-agnostic uncertainty estimation

Multi-task learning with a natural metric for quantitative structure activity relationship learning

The algorithm selection competitions 2015 and 2017

The online performance estimation framework: heterogeneous ensemble learning for data streams

Speeding up algorithm selection using average ranking and active testing by introducing runtime

Massively collaborative machine learning

Case Study on Bagging Stable Classifiers for Data Streams