1 个仓库
Awesome GitHub RepositoriesGlassbox Frameworks
Frameworks specifically designed for training inherently transparent models with verifiable explanations.
Distinct from Model Training Frameworks: Specializes model training frameworks by requiring inherent transparency (glassbox) rather than general utility.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Glassbox Frameworks. Refine with filters or upvote what's useful.
Awesome Glassbox Frameworks 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。
- interpretml/interpret
interpretml/interpret
6,881在 GitHub 上查看Interpret is an interpretable machine learning library and glassbox model framework. It provides toolkits for training inherently transparent models and applying post-hoc explanation techniques to make machine learning predictions human-understandable. The framework distinguishes itself by integrating differential privacy into the training of interpretable models to prevent sensitive data from leaking through explanations. It also features a visualization tool for rendering interactive decision paths and model behavior. The library covers model explainability through feature importance calcu
Ships a system for training inherently transparent models that provide exact and verifiable explanations.
C++
