Obserwuj
Matthias König
Matthias König
Leiden University, RWTH Aachen University, University of Oxford
Zweryfikowany adres z cs.ox.ac.uk
Tytuł
Cytowane przez
Cytowane przez
Rok
Speeding up neural network robustness verification via algorithm configuration and an optimised mixed integer linear programming solver portfolio
M König, HH Hoos, JN Rijn
Machine Learning 111 (12), 4565-4584, 2022
92022
Critically assessing the state of the art in neural network verification
M König, AW Bosman, HH Hoos, JN van Rijn
Journal of Machine Learning Research 25 (12), 1-53, 2024
72024
Towards Algorithm-Agnostic Uncertainty Estimation: Predicting Classification Error in an Automated Machine Learning Setting
M König, HH Hoos, JN van Rijn
7th ICML Workshop on Automated Machine Learning, 2020
72020
Hyper-parameter optimization for latent spaces
B Veloso, L Caroprese, M König, S Teixeira, G Manco, HH Hoos, J Gama
Machine Learning and Knowledge Discovery in Databases. Research Track …, 2021
42021
Speeding Up Neural Network Verification via Automated Algorithm Configuration
M König, HH Hoos, JN van Rijn
ICLR Workshop on Security and Safety in Machine Learning Systems, 2021
42021
Critically Assessing the State of the Art in CPU-based Local Robustness Verification
M König, AW Bosman, HH Hoos, JN van Rijn
Proceedings of the Workshop on Artificial Intelligence Safety 2023 (SafeAI …, 2022
32022
Accelerating Adversarially Robust Model Selection for Deep Neural Networks via Racing
M König, HH Hoos, JN van Rijn
Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI-24), 2024
12024
Automated Design of Linear Bounding Functions for Sigmoidal Nonlinearities in Neural Networks
M König, X Zhang, HH Hoos, M Kwiatkowska, JN van Rijn
Joint European Conference on Machine Learning and Knowledge Discovery in …, 2024
2024
Modelling Concept Drift in Dynamic Data Streams for Recommender Systems
L Caroprese, F Pisani, BM Veloso, M Konig, G Manco, H Hoos, J Gama
ACM Transactions on Recommender Systems, 2024
2024
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–9