My personal repository to keep my Machine Learning study code

In this repository I keep all my relevant code related to my machine learning and data science studies for future reference.

All code here were made for the sake of practice.

Useful material that I used and I think they're good

Here I will compile several links that lead to free materials available online that I used to study machine learning, data science and some basic pre-requisites such as advanced math-related topics. If a link is in this list, them it is because I believe that it was worth my time taking the course and reading the material.

There are many, many, many more left out here in the wild, but the main purpose of this list is to keep only courses that I truly completed from the start until the end.

At the end of this Readme I will build a list with links that lead to very interesting courses that I have not taken so far but I may take in the future.

Full courses that I recommend

Math

1. MIT 18.06 Linear Algebra

   • Resources: Video Lectures, Assigments (with solutions), Exams (with solutions)
   • Instructor: Gilbert Strang
   • Taught in: 2010

2. MIT 18.01 Single Variable Calculus

   • Resources: Video Lectures, Assignments (no solutions), Exams (with solutions)
   • Instructor: David Jerison
   • Taught in: 2006

3. MIT 18.02 Multivariable Calculus

   • Resources: Video Lectures, Assignments (no solutions), Exams (with solutions)
   • Instructor: Denis Auroux
   • Taught in: 2006

Statistics

1. MIT 18.05 Introduction to Probability and Statistics
   • Resources: Assignments (with solutions), Exams (with solutions)
   • Instructors: Jeremy Orloff and Jonathan Bloom
   • Taught in: 2014

Artificial Intelligence

1. MIT 6.034 Articial Intelligence
   • Resources: Video Lectures, Assignments (no solutions), Exams (no solutions)
   • Instructor: Patrick Henry Winston
   • Taught in: 2010

Machine Learning

1. Stanford CS229 Machine Learning

   • Resources:
     • Video Lectures (2018), Assignments (no solutions, depends the year offered), Exams (no solutions, and also depends on the year offered), Course Notes
     • Also check the 2019 summer offering which has extra topics not covered in the 2018 course: video lectures or website.
   • Instructor: Andrew Ng (2018), Anand Avati (2019)
   • Taught in: every year.

2. MIT 6.S191 Introduction to Deep Learning

   • Resources: Video Lectures (2018, 2019, 2020)
   • Instructor: Many.
   • Taught in: every year.

3. Stanford CS231n Convolutional Neural Networks for Visual Recognition

   • Resources: Video Lectures (2017), Assignments (no solutions), Course Notes
   • Instructor: Many (Fei-fei Li, Justin Johnson and Serena Young in 2017's lectures)
   • Taught in: every year.

4. UCL COMPM050/COMPGI13 Introduction to Reinforcement Learning

   • Resources: Video Lectures, Single Assignment (no solution), Single Exam (with solutions)
   • Instructor: David Silver
   • Taught in: 2015

5. Stanford CS234 Reinforcement Learning

   • Resources: Video Lectures. The lecture notes and assignments (no solutions) were previously available in the Stanford website, but I can not find those anymore. Maybe with some luck you can still find somewhere...
   • Instructor: Emma Brunskill
   • Taught in: 2019

6. Coursera Deep Learning Specialization

   • Resources: 5 courses (with 4 weeks each) about basics in Deep Learning, Convolutional Neural Networks, Sequence Models and Machine Learning Projects organization.
   • Instructor and main Assistants: Andre Ng, Kian Katanforoosh, Younes Bensouda Mourri.

7. Coursera Generative Adversarial Networks Specialization

   • Resources: 3 full courses (with 4 weeks each) about building and applying GANs with PyTorch.
   • Instructor and main Assistants: Sharon Zhou, Eda Zhou, Eric Zelikman.

8. Coursera Natural Language Processing Specialization

   • Resources: 4 full courses (with 4 weeks each) about using Statistical Models, Traditional Machine Learning and Deep Learning with text/sequential data.
   • Instructor and main Assistants: Younes Bensouda Mourri, Łukasz Kaiser, Eddy Shyu.

Books

1. An Introduction to Statistical Learning

   • Authors: Gareth James, Daniela Witten, Trevor Hastie and Robert Tibshirani
   • Year: 2013

2. Forecasting: Principles and Practice

   • Authors: Rob J Hyndman and George Athanasopoulos
   • Year: 2018

Miscellaneous blog posts that I recommend

1. Understanding LSTM Networks

   • Author: Christopher Olah
   • Year: 2015

2. Deep Reinforcement Learning: Pong from Pixels

   • Author: Andrej Karpathy
   • Year: 2016

3. Visualizing A Neural Machine Translation Model

   • Author: Jay Alammar
   • Year: 2018

4. The Illustrated Transformer

   • Author: Jay Alammar
   • Year: 2018

5. The Illustrated GPT-2

   • Author: Jay Alammar
   • Year: 2019

6. How GPT3 Works

   • Author: Jay Alammar
   • Year: 2020

7. Transformer Architecture: The Positional Encoding

   • Author: Amirhossein Kazemnejad
   • Year: 2019

Full courses that I haven't taken (until now), but I'm willing to take some time

1. Stanford CS230 Deep Learning

   • Resources: Video Lectures, Links to related papers, Slides.
   • Instructors: Andrew Ng and Kian Katanforoosh
   • Taught in: every year.

2. UC Berkeley CS 285 Deep Reinforcement Learning

   • Resources: Video Lectures, Slides, Assignments (no solutions)
   • Instructores: many.
   • Taught in: 2019/2020.

3. Stanford CS221 Artificial Intelligence: Principles and Techniques

   • Resources: Video Lectures, Lecture Notes, Assignments (with solutions), Exams (with solutions)
   • Instructor: Percy Liang and Dorsa Sadigh
   • Taught in: every year (lectures from 2019)

4. Stanford CS224N Natural Language Processing

   • Resources: Video Lectures, Lecture Notes, Assignments (no solutions)
   • Instructors and coordinator: Chris Manning, Matthew Lamm and Amelie Byun.
   • Taught in: every year (lectures from 2019)