PrototypeCommon
Trustworthy-ML-Lab/Label-free-CBM
[ICLR 23] A new framework to transform any neural networks into an interpretable concept-bottleneck-model (CBM) without needing labeled concept data
- Owner
- Trustworthy-ML-Lab (organization)
- Stars
- Stars: 147
- Forks
- Forks: 37
- Language
- Jupyter Notebook
- License
- None
- Created
- 2023
- Topics
- computer-visiondeep-learningdeep-neural-networksinterpretabilityinterpretable-deep-learning
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Jupyter Notebook
All Jupyter Notebook repos- siddancha/streaming-flow-policyStars: 147Jupyter NotebookPrototype
- interp-reasoning/thought-anchorsStars: 147Jupyter NotebookPrototype
- PacktPublishing/Agentic-Architectural-Patterns-for-Building-Multi-Agent-SystemsStars: 147Jupyter NotebookPrototype
- jstac/quantecon_nyu_2016Stars: 147Jupyter NotebookPrototype
- YaleDHLab/lab-workshopsStars: 147Jupyter NotebookPrototype
- hschen0712/machine-learning-notesStars: 147Jupyter NotebookPrototype