Search Results for author: Christoffer Löffler

Found 4 papers, 1 papers with code

Objective Evaluation of Deep Visual Interpretations on Time Series Data

no code implementations29 Sep 2021 Christoffer Löffler, Wei-Cheng Lai, Lukas M Schmidt, Dario Zanca, Bjoern Eskofier, Christopher Mutschler

(Explanatory) visual interpretation approaches for image and natural language processing allow domain experts to validate and understand almost any deep learning model.

Time Series Time Series Analysis +1

IALE: Imitating Active Learner Ensembles

1 code implementation9 Jul 2020 Christoffer Löffler, Christopher Mutschler

Active learning (AL) prioritizes the labeling of the most informative data samples.

Active Learning Imitation Learning

Overcoming Catastrophic Forgetting via Hessian-free Curvature Estimates

no code implementations25 Sep 2019 Leonid Butyrev, Georgios Kontes, Christoffer Löffler, Christopher Mutschler

Learning neural networks with gradient descent over a long sequence of tasks is problematic as their fine-tuning to new tasks overwrites the network weights that are important for previous tasks.

Cannot find the paper you are looking for? You can Submit a new open access paper.