5 citations · 7 across the 4 of their papers we have counts for
4 papers · 1 filter
Few-shot human motion prediction for heterogeneous sensors
Rafael Rego Drumond, Lukas Brinkmeyer, Lars Schmidt-Thieme
Human motion prediction is a complex task as it involves forecasting variables over time on a graph of connected sensors. This is especially true in the case of few-shot learning,…
Few-Shot Forecasting of Time-Series with Heterogeneous Channels
Lukas Brinkmeyer, Rafael Rego Drumond, Johannes Burchert +1
Learning complex time series forecasting models usually requires a large amount of data, as each model is trained from scratch for each task/data set. Leveraging learning experienc…
HIDRA: Head Initialization across Dynamic targets for Robust Architectures
Rafael Rego Drumond, Lukas Brinkmeyer, Josif Grabocka +1
The performance of gradient-based optimization strategies depends heavily on the initial weights of the parametric model. Recent works show that there exist weight initializations…
Chameleon: Learning Model Initializations Across Tasks With Different Schemas
Lukas Brinkmeyer, Rafael Rego Drumond, Randolf Scholz +2
Parametric models, and particularly neural networks, require weight initialization as a starting point for gradient-based optimization. Recent work shows that a specific initial pa…