2 个仓库
Awesome GitHub RepositoriesClassifier Interpretability
Tools for visualizing and explaining the decision-making process of image classification models.
Distinct from Image Classifiers: Focuses on explaining why an image was classified, rather than performing the classification itself.
Explore 2 awesome GitHub repositories matching data & databases · Classifier Interpretability. Refine with filters or upvote what's useful.
Awesome Classifier Interpretability GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- marcotcr/lime
marcotcr/lime
12,142在 GitHub 上查看This project is an agnostic model interpretability framework and explainability tool designed to provide local interpretable explanations for individual predictions. It functions as a local surrogate model that approximates the behavior of any machine learning classifier or regression model to identify the most influential features for a specific instance. The framework is designed to be model-agnostic, meaning it can explain predictions across tabular, text, and image data regardless of the underlying architecture. It employs local linear approximations and feature importance visualization t
Visualizes the specific segments or pixels of an image that most strongly drive classification decisions.
JavaScript - christophm/interpretable-ml-book
christophM/interpretable-ml-book
5,317在 GitHub 上查看该项目是一个全面的教育资源和技术手册，专注于可解释机器学习和可解释 AI（XAI）。它作为一本教科书和参考资料，用于实现使复杂的机器学习模型对人类透明且易于理解的技术。 该资源提供了关于构建本质上透明的模型（如决策树和稀疏线性模型）以及将事后解释方法应用于黑盒系统的指导。它详细介绍了量化特征重要性、为单个预测生成理由以及使用代理模型近似复杂决策过程的具体方法。 内容涵盖了广泛的分析功能，包括全局和局部特征影响分析、计算机视觉可解释性以及使用 Shapley 值等博弈论贡献。它还通过可解释性评估、识别模型捷径的调试工作流以及透明算法结构的设计来解决模型评估问题。 该项目以 Jupyter Notebooks 集合的形式实现。
Replaces normalization layers with whitening transformations to make pre-trained classifiers intrinsically interpretable.
Jupyter Notebook
