ML_Interpretability

All things ML model interpretability

Currently included tools:

• General:

• Captum Package (https://captum.ai/)
• tf-explain (https://github.com/sicara/tf-explain/) & Visual-Logging (https://github.com/dchaplinsky/visual-logging)

• Natural Language Understanding:

• Directed latet Dirichlet allocation with collapsed Gibbs sampling
• W&B
• Tensorboard