11 citations · 24 across the 11 of their papers we have counts for
11 papers
Latent Space Perspicacity and Interpretation Enhancement (LS-PIE) Framework
Jesse Stevens, Daniel N. Wilke, Itumeleng Setshedi
Linear latent variable models such as principal component analysis (PCA), independent component analysis (ICA), canonical correlation analysis (CCA), and factor analysis (FA) ident…
A Novel and Fully Automated Domain Transformation Scheme for Near Optimal Surrogate Construction
Johann Bouwer, Daniel N. Wilke, Schalk Kok
Recent developments in surrogate construction predominantly focused on two strategies to improve surrogate accuracy. Firstly, component-wise domain scaling informed by cross-valida…
On the momentum diffusion over multiphase surfaces with meshless methods
Johannes C. Joubert, Daniel N. Wilke, Patrick Pizette
This work investigates the effects of the choice of momentum diffusion operator on the evolution of multiphase fluid systems resolved with Meshless Lagrangian Methods (MLM). Specif…
Traction chain networks: Insights beyond force chain networks for non-spherical particle systems
Daniel N. Wilke
Force chain networks are generally applied in granular materials to gain insight into inter-particle granular contact. For conservative spherical particle systems, i.e. frictionles…
GOALS: Gradient-Only Approximations for Line Searches Towards Robust and Consistent Training of Deep Neural Networks
Younghwan Chae, Daniel N. Wilke, Dominic Kafka
Mini-batch sub-sampling (MBSS) is favored in deep neural network training to reduce the computational cost. Still, it introduces an inherent sampling error, making the selection of…
Gradient-only line searches to automatically determine learning rates for a variety of stochastic training algorithms
Dominic Kafka, Daniel Nicolas Wilke
Gradient-only and probabilistic line searches have recently reintroduced the ability to adaptively determine learning rates in dynamic mini-batch sub-sampled neural network trainin…