CodingTrain/Machine-Learning

Examples and experiments around ML for upcoming Coding Train videos

What it solves

This project provides a curated, organized collection of machine learning resources, tutorials, and examples. It helps learners navigate the vast landscape of machine learning by categorizing materials based on difficulty and creative application, making it easier to find relevant study paths.

How it works

The repository acts as a structured directory. It organizes links into specific categories—such as articles, books, courses, projects, and tools—and uses a simple icon-based tagging system to indicate the nature and difficulty level of each resource (e.g., creative, beginner, intermediate, or advanced).

Who it’s for

It is designed for students, developers, and creative practitioners who are interested in machine learning. Whether you are a beginner looking for an introduction or an intermediate learner seeking specific technical examples, the collection offers resources tailored to different skill levels and interests.

Highlights

  • Curated Learning Paths: Includes a wide range of articles, books, and video courses covering everything from foundational concepts to advanced neural networks.
  • Skill-Based Tagging: Uses visual icons to help users quickly identify if a resource is beginner-friendly, advanced, or focused on creative applications.
  • Practical Examples: Features hands-on projects and demos, including reinforcement learning in games and neural network visualizations.
  • Tooling References: Provides a list of libraries and frameworks, with dedicated sections for TensorFlow and t-SNE.

Related

  • Project
    xiaosu200/wm001

    A binary classifier that separates real e-commerce orders from fake 'brushing' orders (fake purchases meant to boost a seller's stats). The README gives no technical details beyond that.

  • Project
    NVIDIA/NVFlare

    NVIDIA FLARE is an open-source Python SDK for federated learning and computing that allows multiple sites to collaborate on AI training and data analysis while keeping their raw data local and secure.

  • Project
    JuliaDiff/ForwardDiff.jl

    A Julia library for computing derivatives, gradients, Jacobians, and Hessians using forward-mode automatic differentiation.

  • Project
    TinyLLaVA/TinyLLaVA_Factory

    A modularized codebase for building and training small-scale large multimodal models, supporting a wide variety of LLMs, vision towers, and connectors.