A structured self-study library covering math foundations, deep learning, transformers, RLHF, and beyond. Begin with the roadmap, follow the phases, then dive deep.
Not sure where to begin? These two documents lay out the complete learning path — from prerequisites to mastery.
A step-by-step guide from zero to mastery. Covers prerequisites, learning milestones, project ideas, and timelines.
Study PlanA day-by-day schedule breaking down exactly what to study each week, with resource links, topic breakdowns, and checkpoints.
Follow the 9-phase journey from mathematical foundations to frontier AI research.
Linear algebra, probability, regression, classification, SVMs, and decision trees — the mathematical and algorithmic bedrock.
Phases 4–6Neural networks, backpropagation, CNNs, RNNs, attention mechanisms, and the transformer revolution that changed everything.
Phases 7–9Large language models, reinforcement learning from human feedback, multimodal AI systems, and open research frontiers.
Go deep on any topic. These comprehensive references cover everything from calculus to diffusion models.
A 600+ page reference covering everything from calculus to diffusion models. Includes detailed proofs, visual explanations, and code examples. Your single deepest resource.
Open TextbookSame textbook content with enhanced typography and formatting, optimized for printing or comfortable offline reading.
Deep DiveAlternative explanations and expanded coverage for tricky topics. Use alongside the main textbook when you need a second perspective.
Explore the bleeding edge — from transformer internals to diffusion models and multimodal systems.
A deep survey of cutting-edge AI/ML research — from transformers and diffusion models to RLHF, multimodal systems, and the nature of intelligence.
IntuitionGo beyond formulas. This document builds lasting mental models and genuine intuitions for core AI/ML concepts — understanding, not just memorizing.
Top books, courses, and tools to accelerate your AI journey. (Disclosure: Some links are affiliate links which help support this site).
The foundational course by Andrew Ng. Master neural networks, hyperparameter tuning, and more. Replace with your affiliate link.
The best practical guide to using Scikit-Learn, Keras, and TensorFlow for real-world projects. Replace with your Amazon Affiliate link.