How to Learn Machine Learning

Table of Contents

1. How to Learn Machine Learning
   1. Background
   2. Introduction
   3. Mathematics
      1. Calculus
      2. Probability and Statistics
         1. Advice
         2. Deep Dives
         3. Probability and Statistics for Machine Learning
            1. Bayesian Statistics
      3. Linear Algebra
      4. Data Analysis
         1. Bayesian Data Analysis
      5. Engineering Mathematics
   4. Engineering
      1. Programming Languages
      2. Tools and Practices
      3. Potpurri
   5. Machine Learning Fundamentals
      1. Statistical Learning
      2. Machine Learning
      3. Probabilistic Machine Learning
      4. Deep Learning
      5. Modern AI
   6. Information - Natural Language Processing, Information Retrieval, Data Mining
      1. NLP and Language Modeling Foundations
      2. Modern Language Modeling and NLP
         1. Transformers for NLP
         2. Modern AI(LLMs)
         3. LLMs
         4. Deep Learning for NLP
         5. Mechanistic Interpretability
      3. Data Mining
   7. Computer Vision
      1. Computer Vision Foundations
      2. Modern Computer Vision
         1. Deep Learning for Computer Vision
         2. Computational Photography
         3. Applied Computer Vision
   8. Audio
      1. Audio Foundations
      2. Music Processing Foundations
      3. Transformers for Audio
      4. Text to Speech
   9. Generative Modeling and Synthesis
      1. Generative Modeling Foundations
      2. Generative Modeling Bleeding Edge - Post-2022
      3. Generative Modeling for Audio
   10. Agents
   11. Applied AI
   12. Bleeding Edge - (Last Updated: July 2026)
       1. Vision Language Models(VLM)
       2. Deep Reinforcement Learning
       3. AI4Science
   13. Human-AI Interaction
       1. Visualization
       2. Creative Coding
   14. Systems - AIML, Distributed, Computer, Data Processing, Data-Centric
       1. Computer Systems Foundations
       2. AI Systems Foundations
       3. Cloud Computing, MLOps
       4. Data Engineering and Feature Engineering
   15. answerAI
       1. Materials
       2. fastAI
       3. answerAI

---

Background

This page is a list of everything that I have found to learn machine learning in the llm chatgpt era. I used a lot of these references during my undergrad and I discovered new resources and courses that helped me study for some of the challenging courses during my time at KTH. Kylie Ying, Chip Huyen, Josh Starmer were a huge inspiration for this page because of how they organized the content on their websites and youtube channels.

Introduction

• The Worlds I See: Curiosity, Exploration, and Discovery at the Dawn of AI by Fei-Fei Li
• Silivia Sapora Interviewing for Machine Learning Positions
• IEEE Spectrum: AI Developer Career Advice
• Chip Huyen A survivor’s guide to Artificial Intelligence
• Chip Huyen ML Ops Guide
• What is Machine Learning?
• How to learn Machine Learning

Mathematics

Calculus

• Utah MATH 1210 - Differential Calculus
• Utah MATH 1220 - Integral Calculus
• Utah MATH 2210 - Multivariable Calculus
• Intro to Derivatives Calculus for Machine Learning
• 3Blue1Brown Essence of Calculus

Probability and Statistics

Advice

• 5 tips for getting better at statistics

  Deep Dives

• Random Variables
• Parameters
• Estimators
• Explaining Probability Distributions
• Parametric Families
• Probability Must-Knows for Machine Learning-Math for ML Part 1
• Statistics: Sampling and Describing Data-Math for ML Part 2
• Random Variables and Normal Distributions-Math for Machine Learning Part 3
• The better way to do statistics - Introduction to Bayesian Statistics
• 3Blue1Brown Bayes Theorem
• 3Blue1Brown Probability of Probabilities
• 3Blue1Brown Central Limit Theorem and the Gaussian Distribution

Probability and Statistics for Machine Learning

• Stanford CS 109 - Probability and Statistics for Computer Scientists
• Stanford CS 109 - Probability and Statistics for Computer Scientists - Lectures
• Steven Brunton - Probability Bootcamp
• Steven Brunton - Introduction to Statistics and Data Analysis

  Bayesian Statistics

  At KTH, one of the required ML courses is DD2434-Advanced Machine Learning which focuses solely on variational inference. This is one of the most mindbending topics and part of the larger class of probabilsitic methods. The concepts appear everywhere in filtering, bayesian modeling, computer vision and audio.

Variational Inference assumes a background in Bayesian Statistics which is usually taught as an advanced graduate statistics class. I came across this series by Ben Lambert after the class which attempts to teach this statistics assuming no statistics background and had I known about it during the class, it would have helped me better understand some of David Blei’s papers which we had to read and implement in this class. I highly recommend this series to understand some of the techniques and math behind variational autoencoders, KL Divergence, and Bayesian Deep Learning.

• A student’s guide to Bayesian Statistics

Linear Algebra

• 3Blue1Brown Essence of Linear Algebra
• MIT 18.06 - Linear Algebra
• Zico Kolter Linear Algebra Refresher

Data Analysis

• Utah CS 3190 - Foundations of Data Analysis

  Bayesian Data Analysis

• Aalto CS-E5710 - Bayesian Data Analysis

Engineering Mathematics

• Kalman and Bayesian Filters in Python
• Digital Signals Theory
• First Principles of Computer Vision - Image Processing I
• First Principles of Computer Vision - Image Processing II
• Hany Farid Computer Vision - Convolution
• Hany Farid Computer Vision - Space and Frequency
• Fundamentals of Music Processing - Fourier Analysis of Signals
• 3B1B Fourier Transform
• 3B1B Convolution
• 3B1B Information Theory

Engineering

Programming Languages

• Python Data Science Handbook
• Python for Data Analysis
• Machine Learning with PyTorch and Scikit-Learn - follow this book if you want to learn PyTorch

  Tools and Practices

• MIT - The Missing Semester of Your CS Education - this course is updating January 2026 to introduce best practices for AIML Engineering. Curtis, Anish, Jonas and company are genius teachers and engineers so this is definitely a must watch
• Utah MSD Git
• Chip Huyen AIE Book Reference

  Potpurri

• Coding Challenges
• Advent of Code
• Sasha Rush LLM-Training-Puzzles
• Sasha Rush GPU-Puzzles
• Sasha Rush Autodiff-Puzzles
• Sasha Rush Tensor-Puzzles
• Sasha Rush Tensor-Puzzles-Penzai
• Sasha Rush Transformer-Puzzles
• Sasha Rush GPTWorld(Prompting Puzzle)
• Neetcode Versus

Machine Learning Fundamentals

• StatQuest

  Statistical Learning

• Statistical Learning With Python

  Machine Learning

• Sebastian Raschka Machine Learning
• Cornell Applied Machine Learning
• KTH DD1420 - Foundations of Machine Learning
• University of Utah CS 6350 - Machine Learning

  Probabilistic Machine Learning

  Probabilistic Machine Learning is probably the most mind-bending machine learning out there. It’s so mind-bending that almost all teaching and reference materials reference Michael I. Jordan and David Blei who not only pioneered applying bayesian statistics to this area but the applications in healthcare, economics, topic modeling, machine learning interpretability and more. Since the area is very broad, programs emphasize different methods: Markov Chain Monte Carlo (MCMC), Metropolis Hastings (MH), Gibbs, Variational Inference. The KTH DD2434 focuses exclusively on variational inference because it underpins the variational-autoencoders (VAE) technique. The courses listed here focus on a mixture of all the methods but for most people who want to understand VAE, I would just recommend focusing on variational inference.

• Probabilistic Machine Learning
• University of Utah CS 6190 - Probabilistic Modeling
• Stanford CS 228 - Probabilistic Graphical Models Notes

  Deep Learning

• Sebastian Raschka Deep Learning
• 3Blue1Brown Neural Networks Lectures 1-4
• Neural Networks Zero to to Hero - Lectures 1-6

Modern AI

• Zico Kolter Modern AI Course

Information - Natural Language Processing, Information Retrieval, Data Mining

NLP and Language Modeling Foundations

• Stanford CS 124 - From Languages to Information
• Stanford CS 124 - From Languages to Information - Lectures
• Stanford CS 124 - From Languages to Information - Course GitHub

  Modern Language Modeling and NLP

  Transformers for NLP

• Hugging Face LLM Course

  Modern AI(LLMs)

• CMU 10-20 - Introduction to Modern AI

  LLMs

• Grant Sanderson Visualizing transformers and attention
• 3Blue1Brown Neural Networks - Lectures 5-8
• Neural Networks Zero to to Hero - Lectures 7, 9-10
• Andrej Karpathy 1 Hour Intro to Large Language Models
• Andrej Karpathy Deep Dive Into LLMs Like ChatGPT

  Deep Learning for NLP

• Utah CS 6340 - Natural Language Processing
• CS 224N Natural Language Processing With Deep Learning

  Mechanistic Interpretability

• Utah CS 6966 - Mechanistic Interpretability

Data Mining

• Utah CS 6140 - Data Mining

Computer Vision

Computer Vision Foundations

• Columbia University - First Principles of Computer Vision
• Hany Farid Computer Vision Lectures

  Modern Computer Vision

  Deep Learning for Computer Vision

• Stanford CS 231N - Deep Learning for Computer Vision
• Stanford CS 231N - Deep Learning for Computer Vision 2025 Lectures

  Computational Photography

• Berkeley CS 180/280A - Intro to Computer Vision and Computational Photography

  Applied Computer Vision

• Hugging Face Computer Vision Course

Audio

Audio Foundations

• Audio Signal Processing for Machine Learning
• Deep Learning For Audio with Python
• PyTorch for Audio and Music Processing
• Audio Data Augmentation

Music Processing Foundations

• PCP Notebooks
• PCPT Notebooks
• FMP Notebooks

Transformers for Audio

• Hugging Face Audio Course

Text to Speech

• Text to Speech and Voice Cloning

Generative Modeling and Synthesis

Generative Modeling Foundations

• Hugging Face Diffusion Course

  Generative Modeling Bleeding Edge - Post-2022

• Cornell - Deep Generative Models
• Stanford CS 236 - Deep Generative Models
• Stanford CS 236 - Deep Generative Models Lectures
• Stanford CS 236 - Deep Generative Model Models Notes

  Generative Modeling for Audio

• Sound Generation with Neural Networks
• Generating Melodies with LSTM
• Generative Music AI
• University of Michigan PAT 463-563 - Music and AI
• University of Michigan PAT 464-564 - Generative AI for Music and Audio Creation

Agents

• Utah CS 6960 - Multimodal LLM Agents

Applied AI

These resources focus mostly on particular tools and libraries for applying recent AIML advancements to industrial problems and applications.

• HuggingFace Courses

Bleeding Edge - (Last Updated: July 2026)

Note - this stuff is beyond my scope of understanding and changing so fast that it’s not organized. Key things to look out for in the news and here: Physical AI, Multimodal AI, 3D AI, Simulation and TBD

Vision Language Models(VLM)

• Berkeley CS 294-43 Large Scale Vision and Language Models
• Flamingo

  Deep Reinforcement Learning

• David Silver DeepMind Reinforcement Learning
• Stanford CS224R - Deep Reinforcement Learning

  AI4Science

• AI for Physicists Tutorial
• Advanced Deep Learning for Physics

Human-AI Interaction

Visualization

• MIT 6/11.C85 - Interactive Data Visualization & Society
• Svelte + D3

  Creative Coding

• Machine Learning for the Web
• Machine Learning for Physical Computing
• Harvard CS 73 - Code, Data, Art
• UChicago Creative Coding
• Golan Levin Experimental Capture Class

Systems - AIML, Distributed, Computer, Data Processing, Data-Centric

Computer Systems Foundations

• Utah CS 4400 - Computer Systems

AI Systems Foundations

• How to Scale Your Models

Cloud Computing, MLOps

• Made With ML
• KTH ID2221 - Data Intensive Computing Platforms
• KTH ID2223 - Scalable Machine Learning and Deep Learning
• MIT 6.584 Distributed Systems

  Data Engineering and Feature Engineering

• MIT Data Centric AI

answerAI

answerAI was founded by Jeremy Howard and Eric Rees in 2023 as a new R&D lab focusing on fundamental research and the development of practical applications based on research breakthroughs. answerAI is the successor to fastAI which was founded by Jeremy Howard and Rachel Thomas. fastAI left a legacy with its machine learning research and highly regarded state of the art machine learning courses that aimed to make deep learning accessible to everyone regardless of their math background which was revolutionary at the time the courses were released. Today fastai’s materials are still used as an entry to the fields of deep learning and generative AI and at the University of San Francisco MS Data Science Program. Jeremy and his team still produce educational videos from time to time on youtube and continue to teach and innovate.

Materials

• Book
• Kaggle Notebooks
• PyTorch Image Models
• FastAI Library

  fastAI

• Lesson 0: How to fastAI
• Part 1: Deep Learning for Coders
• Part 2: From Deep Learning to Stable Diffusion
• Computational Linear Algebra
• Code-First Intro to NLP

  answerAI

• Let’s Build the GPT Tokenizer: A Complete Guide to Tokenization in LLMs
• A Hacker’s Guide to Language Models
• Getting Started with CUDA for Python Progammers
• Going Further with CUDA for Python Progammers
• GPU Programming in the Browser