Julius Martinetz

According to our database, Julius Martinetz authored at least 5 papers between 2022 and 2025.

Collaborative distances:

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

2025

Do Highly Over-Parameterized Neural Networks Generalize Since Bad Solutions are Rare?

Julius Martinetz, Thomas Martinetz

IEEE Trans. Neural Networks Learn. Syst., August, 2025

2024

Rethinking generalization of classifiers in separable classes scenarios and over-parameterized regimes.

Julius Martinetz, Christoph Linse, Thomas Martinetz

Proceedings of the International Joint Conference on Neural Networks, 2024

2022

CorDeep and the Sacrobosco Dataset: Detection of Visual Elements in Historical Documents.

Jochen Büttner, Julius Martinetz, Hassan El-Hajj, Matteo Valleriani

J. Imaging, 2022

An Ever-Expanding Humanities Knowledge Graph: The Sphaera Corpus at the Intersection of Humanities, Data Management, and Machine Learning.

Hassan El-Hajj, Maryam Zamani, Jochen Büttner, Julius Martinetz, Oliver Eberle, Noga Shlomi, Anna Siebold, Grégoire Montavon, Klaus-Robert Müller, Holger Kantz, Matteo Valleriani

Datenbank-Spektrum, 2022

Highly over-parameterized classifiers generalize since bad solutions are rare.

Julius Martinetz, Thomas Martinetz

CoRR, 2022