Marthinus W. Theunissen

According to our database, Marthinus W. Theunissen authored at least 9 papers between 2019 and 2025.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of five.

2025

KnowIt: Deep Time Series Modeling and Interpretation.

Marthinus W. Theunissen, Randle Rabe, Marelie H. Davel

CoRR, July, 2025

2024

Is network fragmentation a useful complexity measure?

Coenraad Mouton, Randle Rabe, Daniël G. Haasbroek, Marthinus W. Theunissen, Hermanus L. Potgieter, Marelie H. Davel

CoRR, 2024

Input Margins Can Predict Generalization Too.

Coenraad Mouton, Marthinus Wilhelmus Theunissen, Marelie H. Davel

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2022

The Missing Margin: How Sample Corruption Affects Distance to the Boundary in ANNs.

Marthinus Wilhelmus Theunissen, Coenraad Mouton, Marelie H. Davel

Proceedings of the Artificial Intelligence Research - Third Southern African Conference, 2022

2021

Pre-interpolation loss behaviour in neural networks.

Arthur E. W. Venter, Marthinus W. Theunissen, Marelie H. Davel

CoRR, 2021

2020

Benign interpolation of noise in deep learning.

Marthinus Wilhelmus Theunissen, Marelie H. Davel, Etienne Barnard

South Afr. Comput. J., 2020

Pre-interpolation Loss Behavior in Neural Networks.

Arthur E. W. Venter, Marthinus W. Theunissen, Marelie H. Davel

Proceedings of the Artificial Intelligence Research, 2020

DNNs as Layers of Cooperating Classifiers.

Marelie H. Davel, Marthinus W. Theunissen, Arnold M. Pretorius, Etienne Barnard

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019

Insights regarding overfitting on noise in deep learning.

Marthinus W. Theunissen, Marelie H. Davel, Etienne Barnard

Proceedings of the South African Forum for Artificial Intelligence Research, 2019