AIX360
DALEX
AIX360 | DALEX | |
---|---|---|
2 | 2 | |
1,533 | 1,323 | |
2.0% | 0.6% | |
8.2 | 5.5 | |
2 months ago | 2 months ago | |
Python | Python | |
Apache License 2.0 | GNU General Public License v3.0 only |
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.
AIX360
- [D] DL Practitioners, Do You Use Layer Visualization Tools s.a GradCam in Your Process?
-
[R] Explaining the Explainable AI: A 2-Stage Approach - Link to a free online lecture by the author in comments
One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques https://arxiv.org/abs/1909.03012 https://github.com/Trusted-AI/AIX360
DALEX
-
Twitter set to accept ‘best and final offer’ of Elon Musk
Which he will not do, because: a) He can't, it's a black box algorithm. It actually is open source already, but that doesn't mean much as it's useless without Twitter's data https://github.com/ModelOriented/DALEX b) He won't release data that shows the algorithm is racist and amplifies conservative and extremist content. He won't remove such functions because it will cost him billions.
-
[D] What are your favorite Random Forest implementations that support categoricals
There are a couple of ways to use Shapley values for explanations in R. One way is to use DALEX, which also contains a lot of other methods besides SHAP. Another one is iml. I am sure there are several other implementations of SHAP as well.
What are some alternatives?
AIF360 - A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.
shapley - The official implementation of "The Shapley Value of Classifiers in Ensemble Games" (CIKM 2021).
explainable-cnn - 📦 PyTorch based visualization package for generating layer-wise explanations for CNNs.
captum - Model interpretability and understanding for PyTorch
cleverhans - An adversarial example library for constructing attacks, building defenses, and benchmarking both
Lime-For-Time - Application of the LIME algorithm by Marco Tulio Ribeiro, Sameer Singh, Carlos Guestrin to the domain of time series classification
DiCE - Generate Diverse Counterfactual Explanations for any machine learning model.
responsible-ai-toolbox - Responsible AI Toolbox is a suite of tools providing model and data exploration and assessment user interfaces and libraries that enable a better understanding of AI systems. These interfaces and libraries empower developers and stakeholders of AI systems to develop and monitor AI more responsibly, and take better data-driven actions.
awesome-shapley-value - Reading list for "The Shapley Value in Machine Learning" (JCAI 2022)
LIME - Tutorial notebooks on explainable Machine Learning with LIME (Original work: https://arxiv.org/abs/1602.04938)
backpack - BackPACK - a backpropagation package built on top of PyTorch which efficiently computes quantities other than the gradient.
catboost - A fast, scalable, high performance Gradient Boosting on Decision Trees library, used for ranking, classification, regression and other machine learning tasks for Python, R, Java, C++. Supports computation on CPU and GPU.