PrototypeCommon
laura-rieger/deep-explanation-penalization
Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584
- Owner
- laura-rieger (personal account)
- Stars
- Stars: 126
- Forks
- Forks: 15
- Language
- Jupyter Notebook
- License
- MIT
- Created
- 2019
- Topics
- interpretabilityneural-networkmachine-learningconvolutional-neural-networkpytorchexplainabilitydeep-learningexplainable-aiartificial-intelligenceml
- Tier
- Prototype (100 to 249 ★) What this tier means
Nearby in Jupyter Notebook
All Jupyter Notebook repos- jamesmontemagno/MonkeyMCPStars: 126Jupyter NotebookPrototype
- Mayankpratapsingh022/DeepSeek-from-ScratchStars: 126Jupyter NotebookPrototype
- togethercomputer/EinsteinArena-new-SOTAStars: 126Jupyter NotebookPrototype
- pyannote/pyannote-coreStars: 126Jupyter NotebookPrototype
- albanie/shot-detection-benchmarksStars: 126Jupyter NotebookPrototype
- greenelab/pancancerStars: 126Jupyter NotebookPrototype