Search Results for author: Daniel Jönsson

Found 3 papers, 1 papers with code

Exploratory Visual Analysis for Increasing Data Readiness in Artificial Intelligence Projects

no code implementations5 Sep 2024 Mattias Tiger, Daniel Jakobsson, Anders Ynnerman, Fredrik Heintz, Daniel Jönsson

We present experiences and lessons learned from increasing data readiness of heterogeneous data for artificial intelligence projects using visual analysis methods.

Neural Activation Patterns (NAPs): Visual Explainability of Learned Concepts

no code implementations20 Jun 2022 Alex Bäuerle, Daniel Jönsson, Timo Ropinski

Promising methods for discovering learned features are based on analyzing activation values, whereby current techniques focus on analyzing high activation values to reveal interesting features on a neuron level.

Classifying the classifier: dissecting the weight space of neural networks

1 code implementation13 Feb 2020 Gabriel Eilertsen, Daniel Jönsson, Timo Ropinski, Jonas Unger, Anders Ynnerman

of neural network classifiers, and train a large number of models to represent the weight space.

16k

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