Directory
Published directory entries matching your search.
A GitHub repository collecting AI learning resources, including over 100 cheat-sheets, free online books, courses, videos and lectures, papers, tutorials, researchers, websites, datasets, conferences, frameworks and tools. Topics include machine learning, deep learning, big data, data science and Python.
A personal blog by a PhD student at Berkeley that hosts notes and posts on data science, programming and machine learning topics. Entries include 15 principles for data scientists, C++11 learning notes, a Mandelbrot fractal in Python and notes from conference talks.
AutoKeras is an AutoML library for deep learning built on Keras, developed by DATA Lab at Texas A&M University. The project describes its goal as making machine learning accessible to everyone. It can be installed with pip, and the documentation states it is currently only compatible with Python 3.7 or later and TensorFlow 2.8.0 or later.
Backprop is a Python library, installable via PyPi, that enables use, finetuning and deployment of machine learning models. It provides task interfaces for conversational question answering, text classification in over 100 languages, image classification, summarisation, emotion detection and text generation, and models can be finetuned with a single line of code.
Cogitare is a modern, fast, modular deep learning and machine learning framework for Python built on top of PyTorch, with a user-friendly interface for beginners and advanced toolsets for experts.
Determined is an open-source machine learning platform that simplifies distributed training, hyperparameter tuning, experiment tracking, and resource management. It works with PyTorch and TensorFlow, offering a Python library, command line interface, and web UI for managing machine learning workflows.
fenn is a Python framework for building machine learning and deep learning workflows and LLM agents. It provides prebuilt trainers, agent templates, logging, and configuration management, with YAML configuration parsed and injected into the entrypoint with CLI override support. It is released under the MIT license.
Gymnasium is an open source Python library for developing and comparing reinforcement learning algorithms. It provides a standard API between learning algorithms and environments, plus reference environments including Classic Control, Box2D, Toy Text, MuJoCo and Atari. It is a fork of OpenAI's Gym library maintained by its maintainers.
Python examples of popular machine learning algorithms with interactive Jupyter demos and math being explained.
Materials for the Hugging Face Diffusion Models Course, a free course on diffusion models. It covers theory, generating images and audio with Diffusers, training and fine-tuning models, and conditional generation. Prerequisites include Python skills and basics in deep learning and PyTorch.
I am trask is a machine learning craftsmanship blog. Posts listed include Decentralized AI in 50 Lines of Python, Is the Universe Random?, Safe Crime Detection, Deep Learning without Backpropagation and Building Safe A.I.
A course on generative modelling, currently unfinished, with the first approximately five lessons mostly done. It covers topics such as PyTorch basics, representations, CLIP, GANs, sequence modelling and transformers. No prior deep learning knowledge is assumed, though comfort with some Python and Jupyter Notebooks is expected.
Apache Mahout builds an environment for quickly creating scalable, performant machine learning applications. Its current work centers on quantum machine learning in Python, with Qumat, a high-level library for writing quantum circuits once and running them on supported backends, and QDP, a GPU-accelerated engine that turns classical data into quantum states. The earlier Mahout Classic codebase is in maintenance mode.
mlpack is a header-only C++ machine learning library with bindings to Python, Julia, R, Go, and the command line. It is built on Armadillo, ensmallen, and cereal and provides implementations of machine learning algorithms. The documentation lists classification, regression, clustering, and preprocessing facilities. It is open source under the 3-clause BSD license.
modAL is a modular active learning framework designed for use with the Python programming language. The project includes introductory documentation, overviews of active learning concepts, usage examples, and quickstart guides. It is hosted as an open source repository on GitHub.
Netron is a viewer for neural network, deep learning and machine learning models. It supports formats including ONNX, TensorFlow Lite, PyTorch, TensorFlow, Core ML, OpenVINO, Keras, Caffe, Darknet, Safetensors and NumPy. It is available as a browser version and installers for macOS, Linux and Windows, plus a Python package. Experimental support exists for MLIR, JAX, GGUF and other formats.
NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.
Open-source, low-code machine learning library in Python that automates machine learning workflows.
TPOT (Tree-based Pipeline Optimization Tool) is a Python automated machine learning tool that optimizes machine learning pipelines using genetic programming. The project underwent a major refactoring, merging what was once called TPOT2 into the main package, with new features including genetic feature selection, multi-objective optimization and an expanded method of defining search spaces.
Adaptive Reliability Layer is a Python project that sits between an inference pipeline and a monitoring layer. It detects distribution shift, decides whether adaptation is warranted, and learns from delayed revealed labels. It does not replace the model.
Annoy is a C++ library with Python bindings for approximate nearest neighbor search. It creates large read-only file-based indexes that are mmapped into memory so many processes can share the same data. Supported distances include Euclidean, Manhattan, cosine, Hamming and dot product.
Bodywork is a command line tool that deploys machine learning pipelines to Kubernetes, handling containers and orchestration. Any pipeline stage runs either a batch job or a long-running process. It is presented as a lightweight alternative to Kubeflow or building a platform around workflow tools such as Apache Airflow, Argo Workflows or Dagster. Stages are defined as Python modules or Jupyter notebooks and configured in a single bodywork.yaml file.
climin is a Python package for optimization that is heavily biased toward machine learning scenarios, distributed under the BSD 3-clause license. It works on top of numpy and partially gnumpy, and was started in winter 2011 by Christian Osendorfer and Justin Bayer.
Dagster is an open source, cloud-native data pipeline orchestrator for the data development lifecycle, with integrated lineage and observability. Users declare data assets as Python functions, and Dagster runs them and keeps assets up to date. It is designed for developing and maintaining data assets such as tables, data sets, machine learning models, and reports.
