Textbooks

These are textbooks/papers that I find really helpful and consult frequently.

Table of Contents

1. Mathematics
   1. Calculus
   2. Linear Algebra
   3. Probability + Statistics
      1. Math Perspective
      2. Computer Science + Machine Learning Perspective
      3. Bayesian Statistics
   4. Mathematics for Machine Learning and Data Driven Problems
2. Data Tools - Programming Languages, Libraries, Frameworks
   1. Programming Languages
   2. Numerical Computing Tools
   3. Machine Learning/Deep Learning
   4. Databases
3. Engineering
4. Systems - AIML, Distributed
5. Machine Learning
   1. Introduction
   2. Statistical Perspective
   3. Applied (Modern + Generative Modeling)
   4. Probabilistic Perspective
      1. Variational Inference
         1. Papers
         2. Deep Dive Explanations
   5. Pattern Matching
   6. Deep Learning
6. Applied Machine Learning
   1. Computer Vision/Image Analysis
   2. Music Informatics
   3. Visualization
   4. Creative Coding
   5. Language Technologies
7. Technical Interviews

---

Mathematics

Calculus

• Calculus by James Stewart - any edition works

Linear Algebra

• Linear Algebra and Its Applications
• Introduction to Linear Algebra
• Think Linear Algebra

  Probability + Statistics

  Math Perspective

• Introduction to Probability

  Computer Science + Machine Learning Perspective

• Probability for Computer Science - Stanford CS 109 Textbook

  Bayesian Statistics

• A Student’s Guide to Bayesian Statistics

Mathematics for Machine Learning and Data Driven Problems

• Data-Driven Science and Engineering: Machine Learning, Dynamical Systems, and Control
• Mathematical Foundations for Data Analysis
• Mathematics for Machine Learning

Data Tools - Programming Languages, Libraries, Frameworks

Programming Languages

• Eloquent JavaScript

Numerical Computing Tools

• Python For Data Analysis
• Python Data Science Handbook

Machine Learning/Deep Learning

• Machine Learning with PyTorch and Scikit-Learn

Databases

• MySQL
• MariaDB
• Postgres
• SQLServer

Engineering

• The Pragmatic Programmer
• Pro Git

Systems - AIML, Distributed

• AI Engineering: Building Applications with Foundation Models
• Designing Machine Learning Systems
• Designing Data-Intensive Applications
• Building Machine Learning Systems with a Feature Store - KTH ID2223 Textbook

Machine Learning

Introduction

• A Course in Machine Learning
• The StatQuest Illustrated Guide to Machine Learning

Statistical Perspective

• An Introduction to Statistical Learning

Applied (Modern + Generative Modeling)

• Volodomyr Kuleshov Notes

Probabilistic Perspective

• Probabilistic Machine Learning: An Introduction - KTH DD2447 Textbook
• Probabilistic Machine Learning: Advanced Topics - KTH DD2434 Textbook, KTH DD2447 Textbook

Variational Inference

Variational Inference is an approximation method in Probabilistic Machine Learning and was the focus of KTH DD2434. It’s very confusing if you are unfamiliar with some of the traditional methods like MCMC, SMC and Bayesian Statistics(this was me when I took the class lol)

Papers

• Variational Inference: A Review for Statisticians
• David Blei Variational Inference Notes
• Stochastic Variational Inference
• Blackbox Variational Inference
• Latent Dirichlet Allocation
• Variational Auto-Encoders

  Deep Dive Explanations

• A brief primer on variational inference
• Machine-Learning Variational Inference
• Variational Bayes and the Mean Field Approximation
• Bruno Magalhaes Blog
• Variational Inference Basics

Pattern Matching

• Pattern Recognition and Machine Learning - KTH DD2434 Textbook

Deep Learning

• Dive Into Deep Learning - KTH DD2424 suggested reading
• Understanding Deep Learning - KTH DD2424 suggested reading
• Deep Learning Foundations and Concepts - KTH DD2424 suggested reading
• Hands-On Machine Learning with Scikit-Learn and PyTorch - KTH ID2223 textbook
• The StatQuest Illustrated Guide to Neural Networks and AI

Applied Machine Learning

Computer Vision/Image Analysis

• Foundations of Computer Vision - Berkeley CS 180 textbook
• Computer Vision Algorithms and Applications - KTH DD2423, Berkeley CS 180 textbook
• Digital Image Processing - KTH DD2423 textbook

Music Informatics

• Fundamentals of Music Processing - KTH DT2470 textbook

Visualization

• Visualization Analysis and Design
• The Grammar of Graphics
• Visualize This
• Data Sketches: A journey of imagination, exploration, and beautiful data visualizations
• The Functional Art
• The Truthful Art
• How Charts Lie
• The Art of Insight

Creative Coding

• The Nature of Code
• The Book of Shaders
• Code as a Creative Medium

Language Technologies

• Natural Language Processing with Python - KTH DD2417 reference textbook
• Speech and Language Processing - KTH DD2417 textbook
• Introduction to Information Retrieval - KTH DD2477 textbook

Technical Interviews

• Chip Huyen Machine Learning Interviews Book
• 100 Numpy Exercises
• Neetcode