Projects
Top Machine Learning projects, ranked by their code.
Model architectures, training loops, optimisation, and classical and deep learning methods: the mathematics and mechanics of learning systems. Each project counts in the one field it is most about, so a single great repository can lead this board.
- Ranked projects
- 59 ranked projects
- Builders
- 9 verified builders
- Builder board
- People rank on the leaderboard
Field
Ranked byProject merit
- 1First67.6AECS-schedulerLibrary / Framework · AdvancedAECS is a PyTorch learning rate scheduler that adjusts the learning rate in real time based on training signals such as gradient norm and loss, switching between four modes (BASELINE, RECOVERY, EXPLORE, STABILIZE) using event-driven logic.Rick
- 2Second67.4ORBITLibrary / Framework · AdvancedThe ORBIT repository provides a Python implementation of the ORBIT optimizer for transformer models with rotary positional embeddings. It includes the optimizer, adapters for external models, baselines, training scripts, and detailed documentation for reproduction and use.Pop Alexandru
- 3=Third66.0modded-GLM-5.3-flash-from-scratchEducational Implementation · AdvancedThe repository is an educational implementation of a hybrid-attention Mixture-of-Experts language model, complete with training scripts, evaluation tools, and theory notebooks for learning and experimentation.Pop Alexandru
- 3, shared rankORBIT-allTraining Experiment · Python66.0AdvancedPop AlexandruMachine Learning
- 05trot-livive-netEducational Implementation · Rust65.5AdvancedJarad PeckenpaughMachine Learning
- 06, shared rankcamera505ML Application · Python64.6Advancedvlad andreiMachine Learning
- 06, shared rankmines-smLibrary / Framework · Rust64.6AdvancedJarad PeckenpaughMachine Learning
- 08ocr-livive-netEducational Implementation · JavaScript63.4AdvancedJarad PeckenpaughMachine Learning
- 09, shared rankmamba-viewAI Developer Tool · Python62.2AdvancedRickMachine Learning
- 09, shared rankResNet_Family-from-scratchArchitecture Reimplementation · Jupyter Notebook62.2AdvancedPop AlexandruMachine Learning
- 11, shared ranksilico-e4b-sae-runML Application · Python62.0AdvancedRickMachine Learning
- 11, shared rankvid-factoryML Application · JavaScript62.0AdvancedJarad PeckenpaughMachine Learning
- 13mamba3-atlas-imageAI Developer Tool · Python61.5AdvancedRickMachine Learning
- 14kernel-workArchitecture Modification / Research · Python60.5AdvancedRickMachine Learning
- 154cast-livive-netEducational Implementation · Rust60.3AdvancedJarad PeckenpaughMachine Learning
- 16, shared rankAurora-SDG-Publication-ClassifierML Application · Python58.9AdvancedJens MittelbachMachine Learning
- 16, shared rankrag-pocEducational Implementation · TypeScript58.9AdvancedJarad PeckenpaughMachine Learning
- 18, shared rankandrej-karpathy-full-courseEducational Implementation · Jupyter Notebook58.6AdvancedPop AlexandruMachine Learning
- 18, shared rankneural-style-transfer-cnnML Application · Python58.6AdvancedPop AlexandruMachine Learning
- 18, shared rankrl-livive-netML Application · JavaScript58.6AdvancedJarad PeckenpaughMachine Learning
- 21LeNet_5-from-scratchArchitecture Reimplementation · Jupyter Notebook57.7ImplementationPop AlexandruMachine Learning
- 22, shared rankcdeEducational Implementation · Python57.4ImplementationJarad PeckenpaughMachine Learning
- 22, shared rankfresta-edgeML Application · Python57.4ImplementationTiago SantosMachine Learning
- 22, shared rankmines-livive-netTraining Experiment · JavaScript57.4ImplementationJarad PeckenpaughMachine Learning
- 25pcap-ml-traffic-classifierML Application · Python56.2ImplementationPop AlexandruMachine Learning
= marks a shared rank: projects with the same merit to one decimal are ranked together.
Who built them
Your work, ranked
Put your projects on the Machine Learning board.
Map your GitHub, then claim your Atlas with a read-only GitHub sign-in. Every AI project of yours that clearly belongs to a field is ranked here and gets its own page you can share.