hi
| Machine Learning | 57 |
|---|---|
| Computer Vision | 41 |
| Data Science | 35 |
| NLP & LLMs | 37 |
| AI Agents | 17 |
| MLOps | 12 |
Each node is one domain, scored only from evidence in these public repositories. Select one to see why.
Substantial implementations with real depth.
4 of 8 public repositories contain AI work and are included in this Atlas. The remaining 4 (repositories without AI code, forks and empty repositories) are excluded from scoring 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.
33% of Atlas Score
The SocrateX library provides a modular framework for building OCR models that combine CNN feature extraction with transformer-based sequence modeling, including components for data handling, training, and inference.
26% of Atlas Score
The repository presents an end-to-end physiological monitoring system that processes ECG and audio signals using a multimodal transformer and adaptive baseline for real-time apnea detection, with a mobile and desktop frontend.
26% of Atlas Score
The repository provides a solution to a cross-modal retrieval challenge that matches constellation geometry to literary texts by averaging coordinates, extracting TF-IDF+SVD text embeddings, learning a Ridge regression mapping, and retrieving via Euclidean similarity.
15% of Atlas Score
The repository is a collection of Jupyter notebooks and Python scripts implementing various machine learning models and algorithms, including reinforcement learning agents, transformer architectures, and GANs. None of the notebooks have been executed, so the code's correctness and output are unverified.
