Login / Signup

A greedy stacking algorithm for model ensembling and domain weighting.

Christoph F KurzWerner MaierChristian Rink
Published in: BMC research notes (2020)
The greedy stacking algorithm provides good ensemble weights and outperforms the linear stacker in many tasks. Still, the brute force approach is slightly superior, but is computationally expensive. The greedy weighting algorithm has a variety of possible applications and is fast and efficient. A python implementation is provided.
Keyphrases
  • machine learning
  • neural network
  • deep learning
  • primary care
  • healthcare
  • working memory
  • convolutional neural network
  • single molecule
  • quality improvement
  • upper limb