Directory
AI education and learning covers courses, roadmaps, and guides for people studying machine learning. Entries include university courses, free video series, reading lists, hands-on notebooks, and roadmaps that map out a path through the field. They assume different starting points, so compare the maths and programming each one expects, whether it uses a current framework, and how much practice comes with the theory. Some are kept by a university or a company, others by one person who may move on, so check when the material was last revised. The field moves quickly, and an older guide can still teach the fundamentals.
A course by Andrej Karpathy on building neural networks from scratch in code, starting with backpropagation basics and building up to modern deep neural networks like GPT. Prerequisites are solid Python programming and intro-level math such as derivatives and gaussians.
NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.
Open-source project that provides AI-assisted learning, courses, tutorials, or study support.
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.
Open-source project that provides AI-assisted learning, courses, tutorials, or study support.
NN Visual is an interactive web-based neural network visualizer. It lets users configure hidden layers, select datasets such as auto_mpg, iris, xor, or mnist, and train a network while observing forward and backpropagation step by step. The tool displays training loss, mean absolute error, weight distributions, and node activation brightness. Written explanations accompany the visualizations to teach concepts like gradient descent, weights, biases, and activation functions without requiring code.
Node-SVM is a GitHub repository that provides support vector machine (SVM) implementations for Node.js. The project enables developers to use SVM algorithms within JavaScript applications. It includes installation instructions, a quick start guide, and an API reference. The repository is open source and contributed to by the community.
numpy-ML is a GitHub-hosted library that implements various machine learning algorithms using only NumPy. The project emphasizes rapid experimentation and can be used as a package. It covers a range of ML methods and includes documentation for users. The repository is open source and welcomes contributions.
Numenta Platform for Intelligent Computing.
NVIDIA AI is a suite of enterprise artificial intelligence solutions offered by NVIDIA. The portfolio includes accelerated infrastructure, enterprise-grade software, and AI models. Solution areas span agentic AI, inference, conversational AI, data science, and cybersecurity. The program aims to help organizations transform into AI-enabled enterprises.
A C++ implementation of an Ordinary Least Squares solver and linear regression engine with zero external dependencies. It uses a custom matrix library, modified Gram-Schmidt orthogonalization and QR decomposition. It includes a CSV test dataset from the Czech film market and computes error metrics such as RSS and MAE.
OpenAI Cookbook is a GitHub repository that provides examples and guides for using the OpenAI API. The collection helps developers integrate OpenAI models into their applications. It includes code samples, best practices, and documentation. The project is open source and accepts community contributions.
OPFython is a GitHub repository offering a Python-inspired implementation of the Optimum-Path Forest classifier. The library enables classification tasks using the optimum-path forest algorithm. It includes installation instructions, quick start guides, and classifier documentation. The project is open source and welcomes contributions from the community.
Orange is an open-source machine learning and data visualization toolbox. It offers visual programming in which widgets are placed on a canvas and connected to load datasets and analyze data. It supports interactive visualization methods including box plots, scatter plots, decision trees, hierarchical clustering, heatmaps, MDS, t-SNE and linear projections. Extensions add text mining, network analysis and other specialized capabilities.
Supports teaching, studying or skills practice with AI-guided learning tools.
Open-source project that provides AI-assisted learning, courses, tutorials, or study support.
Pavlov.js is a reinforcement learning library that uses Markov Decision Processes. It is written in C++ and compiled to JavaScript. The package is installed through npm. Users define transitions and rewards, then call learn to derive a policy and query actions for states.
Perfect TensorFlow is an experimental wrapper of the TensorFlow C API that enables machine learning in server-side Swift. It builds with Swift Package Manager and can be used as part of the Perfect project or as an independent module. The framework conforms to TensorFlow v1.8.0 C API functionality.
Hidden Markov Models for Python, implemented in Cython for speed and efficiency.
Supports teaching, studying or skills practice with AI-guided learning tools.
Prompt Engineering Lil'Log is a blog post focused on prompt engineering for autoregressive language models. It covers methods to steer large language model behavior without updating model weights, including zero-shot prompting, few-shot prompting, and chain-of-thought prompting.
Prophet is a forecasting procedure implemented in R and Python. It provides automated forecasts that can be tuned by hand, and is based on an additive model with non-linear trends and yearly, weekly and daily seasonality plus holiday effects. Facebook released it as open source, available on CRAN and PyPI.
Multidimensional cluster generation in Python.
PyCUDA is a software project associated with Andreas Klöckner, who teaches and conducts research in scientific computing at the University of Illinois at Urbana-Champaign. The project has a dedicated documentation site.
