| Machine Learning | 52 |
|---|---|
| Computer Vision | 16 |
| Data Science | 14 |
| NLP & LLMs | 30 |
| AI Agents | 9 |
| MLOps | 20 |
Each node is one domain, scored only from evidence in these public repositories. Select one to see why.
Substantial implementations with real depth.
4 public repositories → 3 with AI work, evaluated. The other 1 (repositories without AI code, forks and empty repositories) are not scored and have no effect on the result. How repositories are selected
Ordered by how much each project adds to the Atlas score, not by its own score. A project with evidence in several domains can rank above one with a slightly higher project score. Choose a domain to focus on the projects with meaningful evidence there.
49% of Atlas Score
The repository provides an end-to-end system for training Deep Q-Network agents using Apple's MLX framework and generating interactive dashboards to visualize training results, with automated deployment to GitHub Pages.
40% of Atlas Score
The TTB Label Verifier is a prototype application that uses AI-assisted extraction and rule-based comparison to verify alcohol beverage labels against TTB applications. It features a FastAPI backend with a demo extraction mode and a deterministic comparison engine for fields like brand name, alcohol content, and government warnings.
11% of Atlas Score
The repository provides a basic reinforcement learning training script using Apple's MLX framework with random rewards, along with setup instructions. It claims to include automated visualization and a dashboard via GitHub Actions and Pages, but these components were not provided for verification.
