3 papers
cs.LG2020
Neural Power Units
Niklas Heim, Tomáš Pevný, Václav Šmídl
Conventional Neural Networks can approximate simple arithmetic operations, but fail to generalize beyond the range of numbers that were seen during training. Neural Arithmetic Unit…
stat.ML2019
Rodent: Relevance determination in differential equations
Niklas Heim, Václav Šmídl, Tomáš Pevný
We aim to identify the generating, ordinary differential equation (ODE) from a set of trajectories of a partially observed system. Our approach does not need prescribed basis funct…
cs.NE2019
Adaptive Anomaly Detection in Chaotic Time Series with a Spatially Aware Echo State Network
Niklas Heim, James E. Avery
This work builds an automated anomaly detection method for chaotic time series, and more concretely for turbulent, high-dimensional, ocean simulations. We solve this task by extend…