- Learn — understand the central ideas and vocabulary.
- Implement — reproduce a small method without hiding everything behind a library.
- Explain — write a short note about what worked, what failed, and why.

Data engineering
Core systems and architecture
Main
- Designing Data-Intensive Applications — Martin Kleppmann.
- Fundamentals of Data Engineering — Joe Reis and Matt Housley. A practical guide to planning and building robust data systems.
- Database Internals — Alex Petrov. A deeper look at how databases and distributed data systems work.
ML / AI
Core machine learning
Main
- Stanford CS229: Machine Learning — Stanford. Broad foundations, including regression, classification, SVMs, generative models, and introductory deep learning.
- Deep Learning — Ian Goodfellow, Yoshua Bengio, and Aaron Courville. MIT Press textbook with a free official online edition.
- Machine Learning — COMS 4771 — Daniel Hsu, Columbia. Theory-focused ML, generalization, optimization, and statistical foundations.
- CMU ML Core Curriculum — Carnegie Mellon University. Reference for a complete graduate-level core across statistics, optimization, theory, and algorithms.
- Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow, 3rd Edition — Aurélien Géron. Practical machine learning and deep learning with widely used Python libraries.
- StatQuest with Josh Starmer — Josh Starmer. Video explanations of statistics, machine learning, neural networks, and AI.
Build
- The Spelled-Out Intro to Neural Networks and Backpropagation: Building micrograd — Andrej Karpathy. A 2 hour 25 minute walkthrough of neural networks and backpropagation.
Classical AI and decision-making
Main
- Berkeley CS188: Introduction to Artificial Intelligence — UC Berkeley. Search, constraint satisfaction, game playing, probabilistic inference, Markov decision processes, reinforcement learning, and machine learning, with Python projects.
Generative AI, and multimodal models
Main
- Natural Language Processing with Transformers — Lewis Tunstall, Leandro von Werra, and Thomas Wolf. Establish the NLP and Transformer foundation: tokenization, attention, pretrained models, fine-tuning, evaluation, and deployment. The official companion site includes code.
- Hands-On Generative AI with Transformers and Diffusion Models — Omar Sanseviero, Pedro Cuenca, Apolinário Passos, and Jonathan Whitaker. Extend that foundation to generating text, images, and audio with Transformers and diffusion models.
- Vision Language Models — Merve Noyan, Andrés Marafioti, Miquel Farré, and Orr Zohar. Learn multimodal architectures, image-text alignment, training, fine-tuning, and deployment.
- The Ultra-Scale Playbook: Training LLMs on GPU Clusters — Hugging Face / the Nanotron team. Study GPU memory, compute efficiency, communication, and distributed training after becoming comfortable with model training and Transformer architecture.
Computer vision and visual intelligence
- EPFL CS-503: Visual Intelligence — Amir Zamir, EPFL. Classical computer vision, image geometry, correspondence, optical flow, 3D reconstruction, vision Transformers, biological perception, multimodal learning, embodied intelligence, and evaluation.
- CS-503 lecture index — EPFL Graph Search. Indexed lecture descriptions, including image formation and transformation and neuroscience and visual intelligence. The index links to recordings that require EPFL login.
- CS-503 Spring 2026 foundation-model homework — EPFL VILAB. Programming assignments for nanoGPT, nanoMaskGIT, and nano4M: autoregressive generation, masked generation, and multimodal modeling.
- nanoMFM: Multimodal Foundation Models from Scratch — EPFL VILAB. Educational notebooks, exercise stubs, and reference implementations for nanoGPT, nanoMaskGIT, nano4M, nanoFlow (flow matching), and nanoVLM.
- Vision Science: Photons to Phenomenology — Stephen E. Palmer. A reference on visual perception combining psychology, computation, and neuroscience; listed in the CS-503 bibliography.
- The Ecological Approach to Visual Perception — James J. Gibson. Ecological perception, affordances, and the relationship between vision and action; listed in the CS-503 bibliography.
Information retrieval
- Introduction to Information Retrieval — Christopher D. Manning, Prabhakar Raghavan, and Hinrich Schütze. A foundation in search, indexing, ranking, and retrieval evaluation.
Learning theory
- Machine Learning Theory — COMS 4773 — Daniel Hsu, Columbia. Learning theory, sample complexity, PAC-style analysis, and theoretical ML.
- Statistical Learning Theory notes — Columbia. Reference notes on VC dimension, generalization bounds, PAC learning, and learning theory.
- The Nature of Statistical Learning Theory — Vladimir Vapnik. A reference on VC theory, structural risk minimization, and SVM foundations.
Probabilistic machine learning
- Foundations of Graphical Models course readings — David Blei, Columbia. Probabilistic modeling, graphical models, and Bayesian methods.
- Probabilistic Machine Learning: An Introduction and Advanced Topics — Kevin Murphy. Reference books spanning probability, Bayesian ML, graphical models, deep learning, and modern probabilistic ML.
Computer Science
Architecture, hardware, and systems
- Code: The Hidden Language of Computer Hardware and Software, 2nd Edition — Charles Petzold. Builds from binary and logic through CPUs, memory, and operating systems.
- MIT 6.004 Computation Structures — Fall 2018 — MIT. Computer architecture and digital systems lecture series.
- Build a 65C02-Based Computer from Scratch — Ben Eater. Breadboard-computer series, including a “Hello, world” program from scratch on a 6502.
- Core Dumped — Core Dumped. Videos on lower-level computer science, CPUs, and operating system concepts.
Algorithms and computational thinking
- MIT 6.006: Introduction to Algorithms — Spring 2020 — Erik Demaine, Jason Ku, and Justin Solomon. Algorithms and data structures.
- NeetCode Roadmap / NeetCode 150 — NeetCode. Interactive data structures and algorithms roadmap.
- MIT 6.0002: Introduction to Computational Thinking and Data Science — Fall 2016 — Eric Grimson, John Guttag, and Ana Bell. Python, optimization, simulation, probability, and introductory machine learning.
- Spanning Tree — Brian Yu. Computer science video series.
Networks
- Computer Networks and the Internet — Professor Jim Kurose. Lecture series covering topics from Kurose and Ross.
Math
- Mathematics for Machine Learning — Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong. Cambridge textbook with a free official PDF.
Linear algebra
- Introduction to Linear Algebra, 5th Edition — Gilbert Strang. Textbook and supporting materials.
- MIT 18.06 Linear Algebra — Spring 2005 — Gilbert Strang. Full lecture collection; the referenced screenshot is Lecture 33. Also available as a YouTube playlist.
- Essence of Linear Algebra — 3Blue1Brown / Grant Sanderson. Animated video series; the playlist contains 16 videos.
Probability, statistics, and applied mathematics
- A First Course in Probability — Sheldon Ross. Foundational probability text.
- Essential Math for Data Science — Thomas Nield. Applied linear algebra, probability, statistics, and calculus for data science.
- Advanced Engineering Mathematics — Erwin Kreyszig. Applied reference covering calculus, ODEs, PDEs, Fourier methods, and complex analysis.
- Mathematics for Machine Learning — Math Academy — Math Academy. Interactive course in linear algebra, multivariable calculus, probability, and statistics.
Optimization
- Stanford EE364a: Convex Optimization I — lecture slides — Stephen Boyd, Stanford. Convex sets and functions, optimization problems, optimality conditions, duality, and numerical methods, with applications to statistics and ML. Includes a complete slide PDF, examples, and a CVXPY tutorial.
Discrete mathematics
- MIT 6.042J / 18.062J: Mathematics for Computer Science — Spring 2010 — Albert R. Meyer. Discrete mathematics course; the referenced “Quick Summary” slide is from this Spring 2010 course.
- Berkeley CS70: Discrete Mathematics and Probability Theory — Fall 2017 — Kannan Ramchandran and Satish Rao. Logic, proofs, graphs, counting, and probability; a useful preparation resource for CS188.