ML / AI , Data Science Engineering Student
AI-Atlas score
| Machine Learning | 68 |
|---|---|
| Computer Vision | 50 |
| Data Science | 52 |
| NLP & LLMs | 46 |
| AI Agents | 48 |
| MLOps | 56 |
Each node is one domain, scored only from evidence in these public repositories. Select one to see why.
Deep, repeated, well-engineered work in this domain.
8 public repositories → 4 with AI work, evaluated. The other 4 (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.
40% of Atlas Score
TurboWatch is an end-to-end predictive maintenance system for turbofan engines that combines gradient boosting and 1D-CNN remaining useful life models, health monitoring, cost-tuned alarms, SHAP explanations, and a retrieval-augmented generation copilot for querying maintenance manuals, with MLOps for drift detection and champion/challenger retraining.
34% of Atlas Score
The repository contains four AI project proposals (predictive maintenance, RAG assistant, MLOps drift monitoring, and agentic assistant) with supporting code, documentation, and an executed notebook for predictive maintenance. It includes evaluation metrics, tool definitions, and modular code for each proposal.
15% of Atlas Score
This repository provides a local web application for detecting dashboard warning lights in images using a pre-trained YOLO11 model. It includes a metrics page showing model performance, a demo page for interactive image upload and inspection, and tooling for data setup and validation.
11% of Atlas Score
MassMusic is a self-hosted desktop music player that plays local files and YouTube content, imports Spotify playlists, and provides daily personalized recommendations using a Bayesian linear contextual bandit trained on user ratings.
