4 papers
Concept Based Explanations and Class Contrasting
Rudolf Herdt, Daniel Otero Baguer
Explaining deep neural networks is challenging, due to their large size and non-linearity. In this paper, we introduce a concept-based explanation method, in order to explain the p…
Enhancing the analysis of murine neonatal ultrasonic vocalizations: Development, evaluation, and application of different mathematical models
Rudolf Herdt, Louisa Kinzel, Johann Georg Maaà +5
Rodents employ a broad spectrum of ultrasonic vocalizations (USVs) for social communication. As these vocalizations offer valuable insights into affective states, social interactio…
Smooth Deep Saliency
Rudolf Herdt, Maximilian Schmidt, Daniel Otero Baguer +1
In this work, we investigate methods to reduce the noise in deep saliency maps coming from convolutional downsampling. Those methods make the investigated models more interpretable…
Visualize and Paint GAN Activations
Rudolf Herdt, Peter Maass
We investigate how generated structures of GANs correlate with their activations in hidden layers, with the purpose of better understanding the inner workings of those models and b…