The Ultimate FREE Machine Learning Study Plan

A complete study plan to become a Machine Learning Engineer with links to all FREE resources. If you finish the list you will be equipped with enough theoretical and practical experience for the job.

IMPORTANT:

• This list is not sponsored by any of the mentioned links!
• This list takes a lot of time and effort to finish if you want to do it properly!

How to use the Plan:

• For theory lectures: Follow along, take notes, and repeat the notes afterwards
• For practical lectures/courses: Follow along, take notes. If they provide exercises, do them!!! Do not just google the answer, but try to solve it yourself first!
• For coding tutorials: Code along, and after the video try to code it on your own again.

The Plan

0. Prerequisites

• Linear Algebra and Multivariate Calculus
  • Khan Academy - Multivariable Calculus
  • Khan Academy - Differential Equations
  • Khan Academy - Linear Algebra
  • 3Blue1Brown - Essence of Linear Algebra
• Statistics
  • Khan Academy - Statistics Probability
• Python
  • Python Full Course 4 Hours - FreeCodeCamp on YouTube
  • Advanced Python - Playlist on YouTube (Python Engineer)
  • Numpy - Free Udemy Course
  • Matplotlib
    • sentdex - Playlist on YouTube or
    • Corey Schafer - Playlist on Youtube
  • Pandas Tutorial - Playlist on Youtube (Corey Schafer)

1. Basics Machine Learning

• Coursera Free Course by Andrew Ng
• Machine Learning Stanford Full Course on YouTube
• Machine Learning From Scratch - Playlist on YouTube (Python Engineer)
• Books (Optional):
  • Hands-on Machine Learning with Scikit-Learn, Keras, and TensorFlow - Aurélien Géron
  • Python Machine Learning - Sebastian Raschka
  • Introduction to Machine Learning with Python - Andreas Müller

2. Deep Learning

• Stanford Lecture - Convolutional Neural Networks for Visual Recognition
• Learn PyTorch (or Tensorflow)
  • pytorch.org official Tutorials
  • PyTorch Free Course on YouTube (Python Engineer)
• fast.ai - Free Courses
  • Practical Deep Learning for Coders Part 1
  • Part 2

Optional:

• Stanford Lecture - Natural Language Processing with Deep Learning
• Stanford Lecture- Reinforcement Learning

3. Competitions and Own Projects

• Kaggle
  • Datasets (develop own projects)
  • Competitions (start with Getting started section)

4. Prep for Interviews

• https://github.com/alexeygrigorev/data-science-interviews

Next Level

• Make your own projects to show what you have learned.
• Reproduce paper and implement the algorithms.
• Write a blog to explain what you have learned.
• Contribute to ML/DL related open source projects (sklearn, pytorch, fastai, ...).
• Get into Kaggle competitions.

Further readings

• https://towardsdatascience.com/the-cold-start-problem-how-to-break-into-machine-learning-732ee9fedf1d
• https://www.geeksforgeeks.org/how-to-start-learning-machine-learning/
• https://www.youtube.com/watch?v=itzmu0l93wM
• https://elitedatascience.com/learn-machine-learning#step-0
• https://medium.com/@gordicaleksa/get-started-with-ai-and-machine-learning-in-3-months-5236d5e0f230
• https://towardsdatascience.com/beginners-guide-to-machine-learning-with-python-b9ff35bc9c51
• https://www.fast.ai/2019/01/02/one-year-of-deep-learning/

GitHub:

• https://github.com/ZuzooVn/machine-learning-for-software-engineers
• https://github.com/Avik-Jain/100-Days-Of-ML-Code
• https://github.com/yanshengjia/ml-road