Volume 13: AI & Machine Learning

From search algorithms to LLMs, moving programs from rule execution to data-driven decision-making.

Prerequisites

Programming + math fundamentals required. Understand linear algebra and basic probability theory. Complete Vol 10 + Vol 12 first.

Volume note: This volume was moved from its original position as Volume 12 to follow Data Processing & Data Science (Vol 12), because data preprocessing and feature engineering are prerequisites for ML. Content is organized into four layers: Classical AI → Machine Learning → Deep Learning → Modern Generative AI, to avoid the misconception that AI = ML = Deep Learning = LLM.

What's Inside

First learn search and reasoning (Part 1), then master data-driven learning methods (Part 2), dive into the mysteries of neural networks (Part 3), and finally explore how modern large models work and how to use them (Part 4).

Chapter Overview

Part 1: Classical AI

#	Chapter Title	Summary	Prerequisite
1	Search Algorithms	BFS/DFS/A*/Game Trees, Adversarial Search	Vol 2 Graphs
2	Knowledge Representation & Reasoning	Logic, CSP, Bayesian Networks	Vol 10 Math A
3	Reinforcement Learning Basics	MDP, Q-Learning, Policy Gradient	ch1

Part 2: Machine Learning

#	Chapter Title	Summary	Prerequisite
4	Machine Learning Foundations	Data/Features, Train/Validation/Test Sets, Overfitting & Regularization	Vol 12 ch7
5	Linear Models	Linear Regression, Logistic Regression, Regularization	Vol 10 Math C
6	Tree Models & Ensemble	Decision Trees, Random Forest, XGBoost, Bagging/Boosting	ch4
7	Unsupervised Learning	Clustering (K-means/DBSCAN), Dimensionality Reduction (PCA/t-SNE), Anomaly Detection	ch4
8	Model Evaluation & Tuning	Cross-Validation, Confusion Matrix, AUC-ROC, Hyperparameter Search	ch4-5

Part 3: Deep Learning

#	Chapter Title	Summary	Prerequisite
9	Neural Networks Foundations	Perceptron, Backpropagation, Activation Functions, Optimizers	ch5, Math C
10	Advanced Deep Learning	CNN, RNN, Attention, Transformer Architecture	ch9

Part 4: Modern Generative AI

#	Chapter Title	Summary	Prerequisite
11	Pre-training & Fine-tuning	Tokenization, BERT/GPT Pre-training Objectives, Prompt Engineering, Fine-tuning	ch10
12	LLM Principles & Applications	Alignment (RLHF/DPO), RAG, Agent, Evaluation	ch11
13	AI Ethics & Safety	Bias, Explainability, Red Teaming, AI Safety	-
14	AI System Patterns	Cache-Augmented Generation, Multi-Agent Collaboration, Evaluation Frameworks	ch12

Prerequisite knowledge: Programming basics (Vol 1), Vol 10 Math B+C (Probability, Linear Algebra), Vol 12 Data Processing (Feature Engineering)

Completion: Able to distinguish AI/ML/DL/LLM layers; able to independently complete an ML project; understand Transformer principles; understand RAG and Agent basic architectures

---

This volume has 14 chapters, all completed