AI-ML Deep Dives

Every topic rebuilt 3Blue1Brown-style: foundations from zero, the derivation in pictures, worked examples for every scenario, graded exercises, and concept-trap question banks.

361 topics · 1780 pages — more land as generation runs
1.1

Linear Algebra Essentials

1 deep-dive topics
1.2

Calculus & Optimization Basics

14 deep-dive topics
1.3

Probability & Statistics

21 deep-dive topics
1.4

Python & Scientific Computing

12 deep-dive topics
2.1

Data Preprocessing & Feature Engineering

15 deep-dive topics
2.2

Linear & Logistic Regression

16 deep-dive topics
2.3

Tree-Based & Instance Methods

10 deep-dive topics
2.5

Unsupervised Learning

11 deep-dive topics
2.6

Model Evaluation & Selection

16 deep-dive topics
3.1

Neural Network Fundamentals

13 deep-dive topics
3.2

Training Deep Networks

15 deep-dive topics
3.3

Deep Learning Frameworks

11 deep-dive topics
3.4

Convolutional Neural Networks

15 deep-dive topics
3.5

Sequence Models

14 deep-dive topics
4.1

Transformer Architecture

14 deep-dive topics
4.2

Tokenization & Language Modeling

10 deep-dive topics
4.3

Pretraining & Fine-Tuning LLMs

14 deep-dive topics
4.4

Alignment, Prompting & RAG

16 deep-dive topics
4.5

Generative Models

17 deep-dive topics
5.1

Reinforcement Learning Foundations

13 deep-dive topics
5.2

Deep & Advanced RL

14 deep-dive topics
5.3

MLOps & Deployment

18 deep-dive topics
6.1

Scaling & Efficient Architectures

13 deep-dive topics
6.2

AI Agents & Tool Use

10 deep-dive topics
6.3

Interpretability & Explainability

11 deep-dive topics
6.4

AI Safety & Alignment

15 deep-dive topics
6.5

Research Frontiers & Practice

12 deep-dive topics