lucid
shap
lucid | shap | |
---|---|---|
2 | 38 | |
4,613 | 21,677 | |
- | 1.1% | |
0.0 | 9.3 | |
about 1 year ago | 2 days ago | |
Jupyter Notebook | Jupyter Notebook | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
lucid
-
[D] Open source projects for interpretability
You should check out Captum for PyTorch: https://captum.ai/ and tf-explain or lucid (this one is the framework used by distill) for Tensorflow although I think they are both oriented towards Vision interpretability (not sure if you are looking for that).
-
[D] Objective of openAIs Microscope
The optimization objective is trying to find the image that maximizes the activation of a chosen channel/neuron. It uses a process similar to the one in the Lucid (tensorflow) / Lucent (pytorch) library. There are great notebooks included with the libraries and this article has an in-depth explanation of the optimization objectives.
shap
- Shap v0.45.0
-
[D] Convert a ML model into a rule based system
something like GitHub - shap/shap: A game theoretic approach to explain the output of any machine learning model.?
-
[P] tinyshap: A minimal implementation of the SHAP algorithm
A less than 100 lines of code implementation of KernelSHAP because I had a hard time understanding shap's code.
-
What’s after model adequacy?
We use tools like SHAP to explain what the model is doing to stakeholders.
- Feature importance with feature engineering?
-
Model interpretation with many features
https://github.com/slundberg/shap this or https://github.com/marcotcr/lime would be relevant to you, especially if you want to look at explaining a single prediction.
-
SHAP Value Interpretation
See this closed topic for more detail: https://github.com/slundberg/shap/issues/29
-
Christoph Molnar on SHAP Library
Dr. Molnar recently had a semi-viral post on LinkedIn and on Twitter, where he essentially highlights the booming popularity [and power] of using SHAP for explainable AI (which I agree with), but that it also comes with problems; i.e., the open source implementation has thousands of pull requests, bugs, and issues and yet there is no permanent or significant funding to go in and fix them.
-
Random Forest Estimation Question
Option 4) create SHAP values https://github.com/slundberg/shap to better understand what the RF did.
-
Model explainability
txtai pipelines are wrappers around Hugging Face pipelines with logic to easily integrate with txtai's workflow framework. Given that, we can use the SHAP library to explain predictions.
What are some alternatives?
captum - Model interpretability and understanding for PyTorch
shapash - 🔅 Shapash: User-friendly Explainability and Interpretability to Develop Reliable and Transparent Machine Learning Models
machine-learning-experiments - 🤖 Interactive Machine Learning experiments: 🏋️models training + 🎨models demo
Transformer-Explainability - [CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
lucent - Lucid library adapted for PyTorch
pyprobml - Python code for "Probabilistic Machine learning" book by Kevin Murphy
lime - Lime: Explaining the predictions of any machine learning classifier
ML-Workspace - 🛠 All-in-one web-based IDE specialized for machine learning and data science.
interpret - Fit interpretable models. Explain blackbox machine learning.
Animender - An AI that recommends anime based on personal history.
awesome-production-machine-learning - A curated list of awesome open source libraries to deploy, monitor, version and scale your machine learning