Search Results - "Samarin, Maxim"

Learning Extremal Representations with Deep Archetypal Analysis by Keller, Sebastian Mathias, Samarin, Maxim, Arend Torres, Fabricio, Wieser, Mario, Roth, Volker

“…Archetypes represent extreme manifestations of a population with respect to specific characteristic traits or features. In linear feature space, archetypes…”
Get full text

Identifying Soil Erosion Processes in Alpine Grasslands on Aerial Imagery with a U-Net Convolutional Neural Network by Samarin, Maxim, Zweifel, Lauren, Roth, Volker, Alewell, Christine

“…Erosion in alpine grasslands is a major threat to ecosystem services of alpine soils. Natural causes for the occurrence of soil erosion are steep topography…”
Get full text

Investigating causal factors of shallow landslides in grassland regions of Switzerland by Zweifel, Lauren, Samarin, Maxim, Meusburger, Katrin, Alewell, Christine

“…Mountainous grassland slopes can be severely affected by soil erosion, among which shallow landslides are a crucial process, indicating instability of slopes…”
Get full text

On the Empirical Neural Tangent Kernel of Standard Finite-Width Convolutional Neural Network Architectures by Samarin, Maxim, Roth, Volker, Belius, David

“…The Neural Tangent Kernel (NTK) is an important milestone in the ongoing effort to build a theory for deep learning. Its prediction that sufficiently wide…”
Get full text

Mesh-free Eulerian Physics-Informed Neural Networks by Torres, Fabricio Arend, Negri, Marcello Massimo, Nagy-Huber, Monika, Samarin, Maxim, Roth, Volker

“…Physics-informed Neural Networks (PINNs) have recently emerged as a principled way to include prior physical knowledge in form of partial differential…”
Get full text

Learning Invariances with Generalised Input-Convex Neural Networks by Nesterov, Vitali, Torres, Fabricio Arend, Nagy-Huber, Monika, Samarin, Maxim, Roth, Volker

“…Considering smooth mappings from input vectors to continuous targets, our goal is to characterise subspaces of the input domain, which are invariant under such…”
Get full text

Learning Conditional Invariance through Cycle Consistency by Samarin, Maxim, Nesterov, Vitali, Wieser, Mario, Wieczorek, Aleksander, Parbhoo, Sonali, Roth, Volker

“…Identifying meaningful and independent factors of variation in a dataset is a challenging learning task frequently addressed by means of deep latent variable…”
Get full text

Deep Archetypal Analysis by Keller, Sebastian Mathias, Samarin, Maxim, Wieser, Mario, Roth, Volker

“…41th German Conference on Pattern Recognition, GCPR 2019 "Deep Archetypal Analysis" generates latent representations of high-dimensional datasets in terms of…”
Get full text

Learning Extremal Representations with Deep Archetypal Analysis by Keller, Sebastian Mathias, Samarin, Maxim, Torres, Fabricio Arend, Wieser, Mario, Roth, Volker

“…Archetypes are typical population representatives in an extremal sense, where typicality is understood as the most extreme manifestation of a trait or feature…”
Get full text

Computational EEG in Personalized Medicine: A study in Parkinson's Disease by Keller, Sebastian Mathias, Samarin, Maxim, Meyer, Antonia, Kosak, Vitalii, Gschwandtner, Ute, Fuhr, Peter, Roth, Volker

“…Recordings of electrical brain activity carry information about a person's cognitive health. For recording EEG signals, a very common setting is for a subject…”
Get full text