The Little Book of Artificial Intelligence

Version 0.1.10

Author

Duc-Tam Nguyen

Published

September 23, 2025

Contents

Volume 1. First Principles of AI

  1. Defining Intelligence, Agents, and Environments
  2. Objectives, Utility, and Reward
  3. Information, Uncertainty, and Entropy
  4. Computation, Complexity, and Limits
  5. Representation and Abstraction
  6. Learning vs. Reasoning: Two Paths to Intelligence
  7. Search, Optimization, and Decision-Making
  8. Data, Signals, and Measurement
  9. Evaluation: Ground Truth, Metrics, and Benchmarks
  10. Reproducibility, Tooling, and the Scientific Method

Volume 2. Mathematical Foundations

  1. Linear Algebra for Representations
  2. Differential and Integral Calculus
  3. Probability Theory Fundamentals
  4. Statistics and Estimation
  5. Optimization and Convex Analysis
  6. Numerical Methods and Stability
  7. Information Theory
  8. Graphs, Matrices, and Spectral Methods
  9. Logic, Sets, and Proof Techniques
  10. Stochastic Processes and Markov Chains

Volume 3. Data & Representation

  1. Data Lifecycle and Governance
  2. Data Models: Tensors, Tables, Graphs
  3. Feature Engineering and Encodings
  4. Labeling, Annotation, and Weak Supervision
  5. Sampling, Splits, and Experimental Design
  6. Augmentation, Synthesis, and Simulation
  7. Data Quality, Integrity, and Bias
  8. Privacy, Security, and Anonymization
  9. Datasets, Benchmarks, and Data Cards
  10. Data Versioning and Lineage

Volume 4. Search & Planning

  1. State Spaces and Problem Formulation
  2. Uninformed Search (BFS, DFS, Iterative Deepening)
  3. Informed Search (Heuristics, A*)
  4. Constraint Satisfaction Problems
  5. Local Search and Metaheuristics
  6. Game Search and Adversarial Planning
  7. Planning in Deterministic Domains
  8. Probabilistic Planning and POMDPs
  9. Scheduling and Resource Allocation
  10. Meta-Reasoning and Anytime Algorithms

Volume 5. Logic & Knowledge

  1. Propositional and First-Order Logic
  2. Knowledge Representation Schemes
  3. Inference Engines and Theorem Proving
  4. Ontologies and Knowledge Graphs
  5. Description Logics and the Semantic Web
  6. Default, Non-Monotonic, and Probabilistic Logic
  7. Temporal, Modal, and Spatial Reasoning
  8. Commonsense and Qualitative Reasoning
  9. Neuro-Symbolic AI: Bridging Learning and Logic
  10. Knowledge Acquisition and Maintenance

Volume 6. Probabilistic Modeling & Inference

  1. Bayesian Inference Basics
  2. Directed Graphical Models (Bayesian Networks)
  3. Undirected Graphical Models (MRFs/CRFs)
  4. Exact Inference (Variable Elimination, Junction Tree)
  5. Approximate Inference (Sampling, Variational)
  6. Latent Variable Models and EM
  7. Sequential Models (HMMs, Kalman, Particle Filters)
  8. Decision Theory and Influence Diagrams
  9. Probabilistic Programming Languages
  10. Calibration, Uncertainty Quantification, Reliability

Volume 7. Machine Learning Theory & Practice

  1. Hypothesis Spaces, Bias, and Capacity
  2. Generalization, VC, Rademacher, PAC
  3. Losses, Regularization, and Optimization
  4. Model Selection, Cross-Validation, Bootstrapping
  5. Linear and Generalized Linear Models
  6. Kernel Methods and SVMs
  7. Trees, Random Forests, Gradient Boosting
  8. Feature Selection and Dimensionality Reduction
  9. Imbalanced Data and Cost-Sensitive Learning
  10. Evaluation, Error Analysis, and Debugging

Volume 8. Supervised Learning Systems

  1. Regression: From Linear to Nonlinear
  2. Classification: Binary, Multiclass, Multilabel
  3. Structured Prediction (CRFs, Seq2Seq Basics)
  4. Time Series and Forecasting
  5. Tabular Modeling and Feature Stores
  6. Hyperparameter Optimization and AutoML
  7. Interpretability and Explainability (XAI)
  8. Robustness, Adversarial Examples, Hardening
  9. Deployment Patterns for Supervised Models
  10. Monitoring, Drift, and Lifecycle Management

Volume 9. Unsupervised, Self-Supervised & Representation

  1. Clustering (k-Means, Hierarchical, DBSCAN)
  2. Density Estimation and Mixture Models
  3. Matrix Factorization and NMF
  4. Dimensionality Reduction (PCA, t-SNE, UMAP)
  5. Manifold Learning and Topological Methods
  6. Topic Models and Latent Dirichlet Allocation
  7. Autoencoders and Representation Learning
  8. Contrastive and Self-Supervised Learning
  9. Anomaly and Novelty Detection
  10. Graph Representation Learning

Volume 10. Deep Learning Core

  1. Computational Graphs and Autodiff
  2. Backpropagation and Initialization
  3. Optimizers (SGD, Momentum, Adam, etc.)
  4. Regularization (Dropout, Norms, Batch/Layer Norm)
  5. Convolutional Networks and Inductive Biases
  6. Recurrent Networks and Sequence Models
  7. Attention Mechanisms and Transformers
  8. Architecture Patterns and Design Spaces
  9. Training at Scale (Parallelism, Mixed Precision)
  10. Failure Modes, Debugging, Evaluation

Volume 11. Large Language Models

  1. Tokenization, Subwords, and Embeddings
  2. Transformer Architecture Deep Dive
  3. Pretraining Objectives (MLM, CLM, SFT)
  4. Scaling Laws and Data/Compute Tradeoffs
  5. Instruction Tuning, RLHF, and RLAIF
  6. Parameter-Efficient Tuning (Adapters, LoRA)
  7. Retrieval-Augmented Generation (RAG) and Memory
  8. Tool Use, Function Calling, and Agents
  9. Evaluation, Safety, and Prompting Strategies
  10. Production LLM Systems and Cost Optimization

Volume 12. Computer Vision

  1. Image Formation and Preprocessing
  2. ConvNets for Recognition
  3. Object Detection and Tracking
  4. Segmentation and Scene Understanding
  5. 3D Vision and Geometry
  6. Self-Supervised and Foundation Models for Vision
  7. Vision Transformers and Hybrid Models
  8. Multimodal Vision-Language (VL) Models
  9. Datasets, Metrics, and Benchmarks
  10. Real-World Vision Systems and Edge Deployment

Volume 13. Natural Language Processing

  1. Linguistic Foundations (Morphology, Syntax, Semantics)
  2. Classical NLP (n-Grams, HMMs, CRFs)
  3. Word and Sentence Embeddings
  4. Sequence-to-Sequence and Attention
  5. Machine Translation and Multilingual NLP
  6. Question Answering and Information Retrieval
  7. Summarization and Text Generation
  8. Prompting, In-Context Learning, Program Induction
  9. Evaluation, Bias, and Toxicity in NLP
  10. Low-Resource, Code, and Domain-Specific NLP

Volume 14. Speech & Audio Intelligence

  1. Signal Processing and Feature Extraction
  2. Automatic Speech Recognition (CTC, Transducers)
  3. Text-to-Speech and Voice Conversion
  4. Speaker Identification and Diarization
  5. Music Information Retrieval
  6. Audio Event Detection and Scene Analysis
  7. Prosody, Emotion, and Paralinguistics
  8. Multimodal Audio-Visual Learning
  9. Robustness to Noise, Accents, Reverberation
  10. Real-Time and On-Device Audio AI

Volume 15. Reinforcement Learning

  1. Markov Decision Processes and Bellman Equations
  2. Dynamic Programming and Planning
  3. Monte Carlo and Temporal-Difference Learning
  4. Value-Based Methods (DQN and Variants)
  5. Policy Gradients and Actor-Critic
  6. Exploration, Intrinsic Motivation, Bandits
  7. Model-Based RL and World Models
  8. Multi-Agent RL and Games
  9. Offline RL, Safety, and Constraints
  10. RL in the Wild: Sim2Real and Applications

Volume 16. Robotics & Embodied AI

  1. Kinematics, Dynamics, and Control
  2. Perception for Robotics
  3. SLAM and Mapping
  4. Motion Planning and Trajectory Optimization
  5. Grasping and Manipulation
  6. Locomotion and Balance
  7. Human-Robot Interaction and Collaboration
  8. Simulation, Digital Twins, Domain Randomization
  9. Learning for Manipulation and Navigation
  10. System Integration and Real-World Deployment

Volume 17. Causality, Reasoning & Science

  1. Causal Graphs, SCMs, and Do-Calculus
  2. Identification, Estimation, and Transportability
  3. Counterfactuals and Mediation
  4. Causal Discovery from Observational Data
  5. Experiment Design, A/B/n Testing, Uplift
  6. Time Series Causality and Granger
  7. Scientific ML and Differentiable Physics
  8. Symbolic Regression and Program Synthesis
  9. Automated Theorem Proving and Formal Methods
  10. Limits, Fallacies, and Robust Scientific Practice

Volume 18. AI Systems, MLOps & Infrastructure

  1. Data Engineering and Feature Stores
  2. Experiment Tracking and Reproducibility
  3. Training Orchestration and Scheduling
  4. Distributed Training and Parallelism
  5. Model Packaging, Serving, and APIs
  6. Monitoring, Telemetry, and Observability
  7. Drift, Feedback Loops, Continuous Learning
  8. Privacy, Security, and Model Governance
  9. Cost, Efficiency, and Green AI
  10. Platform Architecture and Team Practices

Volume 19. Multimodality, Tools & Agents

  1. Multimodal Pretraining and Alignment
  2. Cross-Modal Retrieval and Fusion
  3. Vision-Language-Action Models
  4. Memory, Datastores, and RAG Systems
  5. Tool Use, Function APIs, and Plugins
  6. Planning, Decomposition, Toolformer-Style Agents
  7. Multi-Agent Simulation and Coordination
  8. Evaluation of Agents and Emergent Behavior
  9. Human-in-the-Loop and Interactive Systems
  10. Case Studies: Assistants, Copilots, Autonomy

Volume 20. Ethics, Safety, Governance & Futures

  1. Ethical Frameworks and Principles
  2. Fairness, Bias, and Inclusion
  3. Privacy, Surveillance, and Consent
  4. Robustness, Reliability, and Safety Engineering
  5. Alignment, Preference Learning, and Control
  6. Misuse, Abuse, and Red-Teaming
  7. Law, Regulation, and International Policy
  8. Economic Impacts, Labor, and Society
  9. Education, Healthcare, and Public Goods
  10. Roadmaps, Open Problems, and Future Scenarios