Resources

The following are some of the resources I have been using to learning programming, CS and stuff in general. There is no order here, just the resources and my comments.

YouTube Channels

• MIT OCW & Stanford Online
  Essentially replacements for my university courses which are not of high standards
• Steve Brunton
  Love the videos on probability, rl and control theory
• The Cherno
  Amazing videos on C, Graphics Programming and Game Engine content
• Two Minute Papers
  “What a time to be alive - with Dr. Károly Zsolnai-Fehér”
• Welch Labs
  Another amazing channel on LLMs and Deep Learning
• Ritvik Math
  Lots of good data science explainers
• 3Blue1Brown
  3B1B is one of the best math youtube channels, especially the linear algebra, calculus introductions and the work with Khan Academy
• Mathemaniac
  Really good animated math videos, similar to 3B1B
• Sebastian Lague
  One of my major inspirations for programming initially, and also really cool coding adventure videos
• Ben Eater
  One of best channels in electronics engineering
• Anton Petrov
  Great explainers on recent science, math and STEM topics
• Artem Kirsanov
  Videos on computational neuroscience. Particularly like the videos where ML is connected to biological learning
• Khan Academy
  The resource I use for learning almost any new foundational concept first.
• diinki
  Arch linux and linux content
• Fireship
  Some of his 100s vids have taught me more than my uni
• freeCodeCamp
  A lot of good content on almost any concept in programming

Books

• Mathematics for Machine Learning
  A great book covering fundamental mathematics as well as machine learning methods in a more igourous format.
• Sheldon Axler
  Standard text for linear algebra
• Sutton & Barto
  A great book to start learning reinforcement learning

These are ofcourse not the only books I have read. I also read biographies, finance & investing books, dark fiction, manga

Paid Resources

I generally do not like to pay for education since it is quite freely available on the internet but sometimes having a structured syllabus feels nice and motivating

• CS50AI on HarvardX
  Short but great course on AI concepts, algorithms and such, with projects and quizzes in each.

• Andrew Ng’s Machine Learning Specializations
  Longer but more comprehensive course with practical labs, quizzes, etc that cover the fundamentals for most of machine learning - nns, decision trees & ensembles, recommender systems, rl, anomaly detection and clustering, etc

• Whartons Business Foundations Specialization
  A comprehensive course that covers marketing, accounting, and a bunch more related to business

Other than these, I have read some foundational research papers in ml and rl