Repository Index

[Legacy] Data & AI Notebook templates catalog organized by tools, following the IMO (input, model, output) framework for easy usage and discovery..

• templates
• opensource
• naas
• notebooks-templates

A library for debugging/inspecting machine learning classifiers and explaining their predictions

• scikit-learn
• machine-learning
• xgboost
• lightgbm

TranslatedCAPTCHA recognition

• captcha-breaking
• keras-tutorials
• deep-learning
• keras

Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.

• data-science
• python
• dag
• data-engineering

TensorFlow Tutorials

• tensorflow-tutorials
• convolutional-neural-networks
• recurrent-neural-networks

Algorithms for outlier, adversarial and drift detection

• anomaly
• outlier
• concept-drift
• detection

2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.

• machine-learning
• python
• statistics
• scikit-learn

An interactive data visualization tool which brings matplotlib graphics to the browser using D3.

Python Productivity for ZYNQ

• pynq

Providing the solutions for high-frequency trading (HFT) strategies using data science approaches (Machine Learning) on Full Orderbook Tick Data.

• high-frequency-trading
• limit-order-book
• python
• machine-learning

Implementing a Neural Network from Scratch

Handout for the tutorial "Creating publication-quality figures with matplotlib"

An unsupervised learning framework for depth and ego-motion estimation from monocular videos

• deep-learning
• depth-prediction
• visual-odometry
• self-supervised-learning

Natural Gradient Boosting for Probabilistic Prediction

• machine-learning
• gradient-boosting
• natural-gradients
• uncertainty-estimation

Code for the ProteinMPNN paper

Python library for interactive topic model visualization. Port of the R LDAvis package.

An experimentation and research platform to investigate the interaction of automated agents in an abstract simulated network environments.

WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.

• rag
• ai-agents
• alignment
• debugging

R kernel for Jupyter

• jupyter
• jupyter-notebook
• jupyter-kernels
• r

Synthetic data generators for tabular and time-series data

• gan-architectures
• gan
• deep-learning
• synthetic-data

The repository host gives no description.

• foundation-model
• gpt
• single-cell

Koç University deep learning framework.

• knet
• deep-learning
• julia
• machine-learning

Python implementation of CMA-ES

ProtTrans is providing state of the art pretrained language models for proteins. ProtTrans was trained on thousands of GPUs from Summit and hundreds of Google TPUs using Transformers Models.