Chapter Index¶

Ch 1: Python Fundamentals for AI
8h · 3 notebooks, 6 exercises, 3 SVGs
Variables, types, control flow, OOP, file I/O, decorators

Ch 2: Data Structures & Algorithms
6h · 3 notebooks, 5 exercises, 3 SVGs
Arrays, Big-O, searching; stacks, queues, sorting; trees, graphs, DP

Ch 3: Linear Algebra & Calculus
10h · 3 notebooks, 5 exercises, 3 SVGs
Vectors, norms; matrices, NumPy; gradients and backpropagation

Ch 4: Probability & Statistics
8h · 3 notebooks, 5 exercises, 3 SVGs
Probability, conditional; distributions, Bayes, CLT; hypothesis testing, A/B tests

Ch 5: Software Design
6h · 3 notebooks, 5 exercises, 3 SVGs
Clean code, PEP 8; design patterns; project structure, testing

Ch 6: Introduction to Machine Learning
8h · 3 notebooks, 5 exercises, 3 SVGs
What is ML, first model; features, evaluation, bias-variance; churn capstone

Ch 7: Supervised Learning
10h · 3 notebooks, 5 exercises, 3 SVGs
Regression, regularization; classification, SVM, ROC; ensembles, tuning, credit-risk

Ch 8: Unsupervised Learning
8h · 3 notebooks, 5 exercises, 3 SVGs
K-Means, hierarchical, DBSCAN; PCA, t-SNE; anomaly detection, customer segmentation

Ch 9: Deep Learning Fundamentals
12h · 3 notebooks, 5 exercises, 3 SVGs
Neural networks from scratch, PyTorch, CNNs, RNNs/LSTMs, image classification

Ch 10: Natural Language Processing Basics
8–10h · 3 notebooks, 2 problem sets, 3 Mermaid diagrams
Tokenization, TF-IDF, embeddings, sentiment, NER, text classification, attention intro

Ch 11: Large Language Models & Transformers
10h · 3 notebooks, 2 problem sets, 3 Mermaid diagrams
Self-attention, transformer architecture, pretrained LLMs, generation strategies

Ch 12: Prompt Engineering & In-Context Learning
6h · 3 notebooks, 2 problem sets, Mermaid diagrams
Prompt patterns, few-shot, chain-of-thought, system prompts, generation params

Ch 13: Retrieval-Augmented Generation
8h · 3 notebooks, 2 problem sets, Mermaid diagrams
Embeddings, vector search, RAG architecture, chunking, evaluation

Ch 14: Fine-tuning & Adaptation
8h · 3 notebooks, 2 problem sets, Mermaid diagrams
Full fine-tuning, LoRA/QLoRA, instruction tuning, evaluation, cost trade-offs

Ch 15: MLOps & Model Deployment
8h · 3 notebooks, 2 problem sets, 3 Mermaid diagrams
Packaging, FastAPI serving, registries, CI/CD, drift monitoring

Ch 16: Multi-Agent Systems Architecture
10h · 3 notebooks, 2 problem sets, 3 Mermaid diagrams
Agents, message passing, Contract-Net allocation, consensus, orchestration

Ch 17: Advanced RAG & Knowledge Systems
10h · 3 notebooks, 2 problem sets, 2 Mermaid diagrams
BM25, dense retrieval, Reciprocal Rank Fusion, reranking, retrieval metrics

Ch 18: Reinforcement Learning Fundamentals
12h · 3 notebooks, 2 problem sets, 2 Mermaid diagrams
MDPs, value functions, Q-learning on a gridworld, policy gradients

Ch 19: Model Optimization & Inference
8h · 3 notebooks, 2 problem sets, 2 Mermaid diagrams
int8 quantization, pruning, knowledge distillation, latency vs throughput

Ch 20: Building Production AI Systems
10h · 3 notebooks, 2 problem sets, 2 Mermaid diagrams
Rate limiting, circuit breakers, canary rollouts, observability, SLOs

Ch 21: AI for Finance
10h · 3 notebooks, 2 problem sets, 2 Mermaid diagrams
Returns, Sharpe, drawdown, MA-crossover strategy, honest backtesting

Ch 22: AI Safety & Alignment
8h · 3 notebooks, 2 problem sets, 2 Mermaid diagrams
Content filtering, reward models/RLHF, fairness metrics, red-teaming

Ch 23: Building Your Own AI Products
8h · 3 notebooks, 2 problem sets, 2 Mermaid diagrams
RICE prioritization, unit economics (LTV/CAC), retention, funnels

Ch 24: Research & Cutting-Edge Techniques
8h · 3 notebooks, 2 problem sets, 2 Mermaid diagrams
Reading papers, attention from scratch, mixture-of-experts in NumPy

Ch 25: AI Governance & Ethics
6h · 3 notebooks, 2 problem sets, 2 Mermaid diagrams
EU AI Act risk tiers, model cards, risk matrices, accountability