Ctrl K

Explainable embeddings

Experiments with regard to explanation of embedded spaces and multi modal models.

2
contributors
Get started
114 commitsLast commit ≈ 4 months ago2 stars1 fork

Description

  • Experiments to tune our explainable AI method in DIANNA.

Our method explains what parts of a data item causes it to come closer to or move further from some other data item in the same embedded space.

Keywords
DIANNA
Embedded spaces
Explainable AI
Programming languages
  • Jupyter Notebook 99%
  • Python 1%
License
</>Source code

Participating organisations

Netherlands eScience Center

Contributors

Christiaan Meijer
Christiaan Meijer
RSE
Netherlands eScience Center
Patrick Bos
Patrick Bos
RSE
Netherlands eScience Center

Related projects

Explainable Embeddings

What is happening in your machine-learned embedded spaces?

Updated 5 months ago
Finished

DIANNA - Deep Insight and Neural Networks Analysis

Explainable AI tool for scientists

Updated 11 months ago
Finished