kaieye/2022-machine-learning-specialization

★ 4,603Jupyter NotebookAudience · developerComplexity · 2/5Setup · easy

Mindmap

mindmap
  root((repo))
    What it does
      Course lab notebooks
      Jupyter exercises
    Courses covered
      Supervised learning
      Advanced algorithms
      Unsupervised learning
    Tech stack
      Python
      Jupyter Notebook
    Setup
      Python 3.7.6
      pip install

mindmap root((repo)) What it does Course lab notebooks Jupyter exercises Courses covered Supervised learning Advanced algorithms Unsupervised learning Tech stack Python Jupyter Notebook Setup Python 3.7.6 pip install

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Run Andrew Ng's machine learning course exercises locally on your own computer

USE CASE 2

Practice implementing regression and classification algorithms in Python notebooks

USE CASE 3

Study unsupervised learning and reinforcement learning through interactive labs

USE CASE 4

Follow the 2022 Coursera ML Specialization exercises offline with all code pre-loaded

Tech stack

PythonJupyter Notebook

Getting it running

Difficulty · easy Time to first run · 30min

Requires Python 3.7.6, install all dependencies with a single pip command from the included requirements file.

In plain English

This repository contains the course code and lab materials for Andrew Ng's 2022 Machine Learning Specialization, a three-part course series offered on Coursera. The materials here are notebooks and exercises that go alongside the video lectures, not a standalone learning resource on their own. The specialization is split into three courses. The first covers supervised learning, focusing on regression (predicting a number) and classification (predicting a category). The second covers more advanced learning algorithms. The third covers unsupervised learning, recommendation systems, and reinforcement learning. The repository's README is bilingual in Chinese and English. It provides links to the official Coursera course page, course slides hosted by deeplearning.ai, and a video reupload on Bilibili for viewers in China. The author notes that course code and test content have been fully updated and welcomes pull requests to add supplementary notes or improve existing markdown files. To run the notebooks locally, you install Python (the course used version 3.7.6) and then install the required packages with a single pip command. No other setup is described in the README. This is a companion repository for an existing course, not an independent textbook or software project. It is most useful if you are already enrolled in or watching the 2022 version of Andrew Ng's machine learning course and want to run the exercises on your own machine.

Copy-paste prompts

Prompt 1

I'm working through the kaieye/2022-machine-learning-specialization notebooks. I'm stuck on the gradient descent exercise in Course 1. Walk me through what each step does and why it works.

Prompt 2

Using the logistic regression notebook from kaieye/2022-machine-learning-specialization, explain what the cost function is doing in plain English without requiring math background.

Prompt 3

Help me understand the reinforcement learning section from Course 3 of the 2022 ML Specialization. What does Q-learning do and how does the notebook example demonstrate it?

Prompt 4

I want to run kaieye/2022-machine-learning-specialization notebooks locally. Walk me through installing Python 3.7.6 and getting the first exercise notebook running.

Open on GitHub → Explain another repo

← kaieye on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.