Search Results for author: Maike Rees

Found 4 papers, 2 papers with code

Classification-by-Components: Probabilistic Modeling of Reasoning over a Set of Components

1 code implementation NeurIPS 2019 Sascha Saralajew, Lars Holdijk, Maike Rees, Ebubekir Asan, Thomas Villmann

The decomposition of objects into generic components combined with the probabilistic reasoning provides by design a clear interpretation of the classification decision process.

Adversarial Attack Classification +1

Robustness of Generalized Learning Vector Quantization Models against Adversarial Attacks

1 code implementation1 Feb 2019 Sascha Saralajew, Lars Holdijk, Maike Rees, Thomas Villmann

The evaluation suggests that both Generalized LVQ and Generalized Tangent LVQ have a high base robustness, on par with the current state-of-the-art in robust neural network methods.

Quantization

Cannot find the paper you are looking for? You can Submit a new open access paper.