Search Results for author:
Found 4 papers, 4 papers with code
Few-shot human motion prediction for heterogeneous sensors
Human motion prediction is a complex task as it involves forecasting variables over time on a graph of connected sensors.
Few-Shot Forecasting of Time-Series with Heterogeneous Channels
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.
HIDRA: Head Initialization across Dynamic targets for Robust Architectures
In this paper, we present HIDRA, a meta-learning approach that enables training and evaluating across tasks with any number of target variables.
Chameleon: Learning Model Initializations Across Tasks With Different Schemas
Parametric models, and particularly neural networks, require weight initialization as a starting point for gradient-based optimization.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
