Contents
Home
AI Timeline AI Landscape Guide to Major Papers Modern Reading Guide
Compendium
All parts & chapters →
IMathematical Foundations
01Linear Algebra 02Calculus & Differential Equations 03Optimization Theory 04Probability Theory 05Statistics & Statistical Inference 06Information Theory 07Bayesian Reasoning 08Signal Processing
IIProgramming & Software Engineering
01Python for Data Science 02Scientific Computing 03Algorithms & Data Structures 04Software Engineering Principles 05Databases & SQL 06Version Control & Collaborative Development
IIIData Engineering & Systems
01Data Collection & Acquisition 02Data Storage & Warehousing 03Data Pipelines & Orchestration 04Streaming & Real-Time Data 05Distributed Computing 06Cloud Platforms & Infrastructure 07Data Quality, Governance, & Metadata
IVClassical Machine Learning
01Supervised Learning: Regression 02Supervised Learning: Classification 03Ensemble Methods 04Unsupervised Learning: Clustering 05Dimensionality Reduction 06Probabilistic Graphical Models 07Kernel Methods & SVMs 08Feature Engineering & Selection 09Model Evaluation & Selection
VDeep Learning Foundations
01Neural Network Fundamentals 02Training Deep Networks 03Regularization & Generalization 04Convolutional Neural Networks 05Sequence Models 06Attention Mechanisms 07Transfer Learning & Pretraining
VINLP & Large Language Models
01NLP Fundamentals 02Classical NLP 03Word Embeddings & Distributional Semantics 04The Transformer Architecture 05Pretraining Paradigms 06LLMs: Scale & Emergent Capabilities 07Instruction Tuning & Alignment 08Fine-Tuning & Parameter-Efficient Adaptation 09Retrieval-Augmented Generation 10LLM Evaluation
VIIComputer Vision
01Image Representation & Classical Vision 02Modern Image Classification & Architectures 03Object Detection & Instance Segmentation 04Video Understanding 053D Vision & Spatial Understanding 06Vision-Language Models
VIIISpeech, Audio & Music
01Audio Signal Processing 02Automatic Speech Recognition 03Text-to-Speech & Voice Synthesis 04Speaker Recognition & Verification 05Speaker Diarization 06Audio Classification & Sound Understanding 07Music Generation & Music AI
IXReinforcement Learning
01RL Fundamentals 02Tabular RL 03Deep Q-Networks & Value-Based Methods 04Policy Gradient & Actor-Critic Methods 05Model-Based RL & World Models 06Multi-Agent Reinforcement Learning 07Offline RL & Imitation Learning 08Preference Learning & RLHF
XGenerative Models
01Variational Autoencoders 02Generative Adversarial Networks 03Normalizing Flows 04Diffusion Models 05Autoregressive Generative Models 06Image & Video Generation 073D & Multimodal Generation 08Multimodal Foundation Models
XIAI Agents & Autonomous Systems
01Agent Fundamentals 02LLM-Based Agents 03Planning & Reasoning 04Memory & Knowledge Management 05Tool Use & Function Calling 06Computer Use & GUI Agents 07Agent Frameworks & Infrastructure 08Multi-Agent Systems 09Agent Safety, Control & Oversight 10Agent Evaluation & Benchmarking 11Using AI Agents: Getting Started 12Building AI Agents: A Practitioner's Handbook
XIIRobotics & Embodied AI
01Robot Perception & Sensing 02Motion Planning & Control 03Learning from Demonstration & Imitation 04Sim-to-Real Transfer 05Foundation Models for Robotics 06Autonomous Vehicles
XIIISpecialized ML Methods
01Time Series Analysis & Forecasting 02Anomaly Detection 03Causal Inference 04Causal Machine Learning 05Graph Neural Networks 06Survival Analysis & Event Modeling 07Bayesian Deep Learning 08Meta-Learning & Few-Shot Learning 09Continual & Lifelong Learning 10Federated Learning & Privacy-Preserving ML 11Neurosymbolic AI
XIVApplied Domains
01Recommender Systems 02Search & Information Retrieval 03Intro to Finance & Economics 04Financial ML & Quantitative Methods 05Healthcare & Clinical AI 06Intro to Cybersecurity 07AI for Cybersecurity 08AI for Education & Personalization 09AI for Manufacturing & Operations 10Human-AI Interaction & UX
XVAI for Science
01Scientific Machine Learning 02Intro to Chemistry 03Protein Science & AI 04Biology, Genomics & AI 05Pharmacology, Drug Discovery & AI 06Climate, Earth Systems & AI 07Physics & AI 08Materials Science & AI 09Astronomy & Astrophysics & AI 10AI for Mathematics
XVIMLOps & Production ML
01Experiment Tracking & Reproducibility 02Feature Stores & Data Management for ML 03Model Deployment & Serving 04Model Monitoring & Drift Detection 05CI/CD for Machine Learning 06A/B Testing & Causal Experimentation 07Responsible Release & Deployment Practices
XVIIAI Infrastructure & Systems
01Hardware for ML 02Distributed Training 03Model Compression 04Inference Optimization 05AI Chips & Custom Silicon
XVIIIAI Safety, Alignment & Governance
01AI Safety Fundamentals 02Technical Alignment Methods 03Robustness & Adversarial ML 04Mechanistic Interpretability 05Explainability for Practitioners 06Fairness, Bias & Equity 07Privacy in ML 08AI Governance, Policy & Regulation
The Compendium · 2026 Edition

The map of modern AI.

Each chapter is intended to stand alone as a self-contained guide — long enough to teach, short enough to read in an evening. What's ready is marked; everything else is on the way.

Part I

Mathematical Foundations

  1. 01
    Linear AlgebraAvailable
    vectors, matrices, decompositions, eigenvalues
  2. 02
    Calculus & Differential EquationsAvailable
    multivariable calculus, ODEs, PDEs as relevant to physics-informed ML
  3. 03
    Optimization TheoryAvailable
    convexity, gradient descent, Lagrangians, constrained optimization
  4. 04
    Probability TheoryAvailable
    random variables, distributions, expectation, concentration inequalities
  5. 05
    Statistics & Statistical InferenceAvailable
    frequentist inference, hypothesis testing, regression, experimental design
  6. 06
    Information TheoryAvailable
    entropy, KL divergence, mutual information, compression
  7. 07
    Bayesian ReasoningAvailable
    Bayes' theorem, priors, posteriors, conjugacy, hierarchical models
  8. 08
    Signal ProcessingAvailable
    Fourier transforms, convolution, filtering, sampling — prerequisite for audio and time series
Part II

Programming & Software Engineering

  1. 01
    Python for Data ScienceAvailable
    Python idioms, data manipulation with pandas, NumPy
  2. 02
    Scientific ComputingAvailable
    SciPy, numerical methods, linear algebra libraries
  3. 03
    Algorithms & Data StructuresAvailable
    complexity, trees, graphs, hashing — what ML practitioners actually need
  4. 04
    Software Engineering PrinciplesAvailable
    clean code, testing, design patterns, documentation
  5. 05
    Databases & SQLAvailable
    relational databases, query optimization, NoSQL overview
  6. 06
    Version Control & Collaborative DevelopmentAvailable
    Git, code review, branching strategies
Part III

Data Engineering & Systems

  1. 01
    Data Collection & AcquisitionAvailable
    web scraping, APIs, data procurement, synthetic data
  2. 02
    Data Storage & WarehousingAvailable
    data lakes, warehouses, columnar formats, Parquet, Delta Lake
  3. 03
    Data Pipelines & OrchestrationAvailable
    Airflow, Prefect, dbt, batch vs. stream pipelines
  4. 04
    Streaming & Real-Time DataAvailable
    Kafka, Flink, event-driven architectures
  5. 05
    Distributed ComputingAvailable
    Spark, MapReduce, distributed data processing
  6. 06
    Cloud Platforms & InfrastructureAvailable
    AWS, GCP, Azure — services relevant to data and ML
  7. 07
    Data Quality, Governance, & MetadataAvailable
    data contracts, lineage, cataloging, observability
Part IV

Classical Machine Learning

  1. 01
    Supervised Learning: RegressionAvailable
    linear and polynomial regression, regularization, generalized linear models
  2. 02
    Supervised Learning: ClassificationAvailable
    logistic regression, decision trees, Naive Bayes, kNN
  3. 03
    Ensemble MethodsAvailable
    bagging, boosting, random forests, gradient boosting, XGBoost
  4. 04
    Unsupervised Learning: ClusteringAvailable
    k-means, DBSCAN, hierarchical clustering, Gaussian mixture models
  5. 05
    Dimensionality ReductionAvailable
    PCA, ICA, t-SNE, UMAP, autoencoders
  6. 06
    Probabilistic Graphical ModelsAvailable
    Bayesian networks, Markov random fields, HMMs
  7. 07
    Kernel Methods & Support Vector MachinesAvailable
    the kernel trick, SVMs, Gaussian processes seen from above
  8. 08
    Feature Engineering & SelectionAvailable
    encoding, interaction terms, mutual information, wrapper and filter methods
  9. 09
    Model Evaluation & SelectionAvailable
    cross-validation, metrics, calibration, overfitting, leakage
Part V

Deep Learning Foundations

  1. 01
    Neural Network FundamentalsAvailable
    perceptrons, backpropagation, activation functions, MLPs
  2. 02
    Training Deep NetworksAvailable
    optimizers — SGD, Adam, scheduling — initialization, batch size
  3. 03
    Regularization & GeneralizationAvailable
    dropout, weight decay, data augmentation, early stopping
  4. 04
    Convolutional Neural NetworksAvailable
    convolutions, pooling, receptive fields, classic architectures
  5. 05
    Sequence ModelsAvailable
    RNNs, LSTMs, GRUs, vanishing gradients, sequence-to-sequence
  6. 06
    Attention MechanismsAvailable
    soft and hard attention, self-attention, cross-attention, multi-head attention
  7. 07
    Transfer Learning & PretrainingAvailable
    fine-tuning, domain adaptation, representation learning
Part VI

Natural Language Processing & Large Language Models

  1. 01
    NLP FundamentalsAvailable
    tokenization, morphology, POS tagging, parsing, linguistic structure
  2. 02
    Classical NLPAvailable
    bag of words, TF-IDF, n-grams, named entity recognition, information extraction
  3. 03
    Word Embeddings & Distributional SemanticsAvailable
    Word2Vec, GloVe, fastText, contextualized representations
  4. 04
    The Transformer ArchitectureAvailable
    encoder, decoder, positional encoding, layer norm, architecture variants
  5. 05
    Pretraining ParadigmsAvailable
    masked LM, causal LM, encoder-only, decoder-only, encoder-decoder
  6. 06
    Large Language Models: Scale & Emergent CapabilitiesAvailable
    scaling laws, emergent behaviors, capabilities and limitations
  7. 07
    Instruction Tuning & AlignmentAvailable
    RLHF, DPO, Constitutional AI, preference learning
  8. 08
    Fine-Tuning & Parameter-Efficient AdaptationAvailable
    full fine-tuning, LoRA, prefix tuning, adapters, model merging
  9. 09
    Retrieval-Augmented GenerationAvailable
    dense retrieval, hybrid search, RAG architectures, long-context tradeoffs
  10. 10
    LLM EvaluationAvailable
    benchmarks, contamination, human evaluation, critique of leaderboards
Part VII

Computer Vision

  1. 01
    Image Representation & Classical VisionAvailable
    pixel statistics, color spaces, edge detection, classical feature descriptors
  2. 02
    Modern Image Classification & ArchitecturesAvailable
    ResNets, EfficientNets, Vision Transformers, scaling
  3. 03
    Object Detection & Instance SegmentationAvailable
    YOLO, Faster R-CNN, DETR, SAM
  4. 04
    Video UnderstandingAvailable
    temporal modeling, optical flow, action recognition, video transformers
  5. 05
    3D Vision & Spatial UnderstandingAvailable
    depth estimation, point clouds, NeRF, 3D reconstruction
  6. 06
    Vision-Language ModelsAvailable
    CLIP, image captioning, visual question answering, grounding
Part VIII

Speech, Audio & Music

  1. 01
    Audio Signal ProcessingAvailable
    waveforms, spectrograms, MFCCs, mel filterbanks
  2. 02
    Automatic Speech RecognitionAvailable
    CTC, attention-based, Whisper, streaming ASR
  3. 03
    Text-to-Speech & Voice SynthesisAvailable
    WaveNet, Tacotron, neural vocoding, voice cloning
  4. 04
    Speaker Recognition & VerificationAvailable
    speaker embeddings, i-vectors, x-vectors, ECAPA-TDNN, verification, anti-spoofing
  5. 05
    Speaker DiarizationAvailable
    VAD, segmentation, AHC, spectral clustering, EEND, speaker-attributed transcription, DER
  6. 06
    Audio Classification & Sound UnderstandingAvailable
    environmental sound, music tagging, sound event detection
  7. 07
    Music Generation & Music AIAvailable
    symbolic music, audio generation, MusicLM-style models
Part IX

Reinforcement Learning

  1. 01
    RL FundamentalsAvailable
    MDPs, Bellman equations, value functions, policies, exploration
  2. 02
    Tabular RLAvailable
    Q-learning, SARSA, dynamic programming, model-based planning
  3. 03
    Deep Q-Networks & Value-Based MethodsAvailable
    DQN, double DQN, dueling networks, Rainbow
  4. 04
    Policy Gradient & Actor-Critic MethodsAvailable
    REINFORCE, A3C, PPO, SAC, TD3
  5. 05
    Model-Based RL & World ModelsAvailable
    Dyna, Dreamer, MBPO, planning with learned models
  6. 06
    Multi-Agent Reinforcement LearningAvailable
    cooperative, competitive, emergent behavior
  7. 07
    Offline RL & Imitation LearningAvailable
    behavior cloning, inverse RL, conservative Q-learning
  8. 08
    Preference Learning & RLHFAvailable
    reward modeling, human feedback, RLAIF
Part X

Generative Models

  1. 01
    Variational AutoencodersAvailable
    ELBO, reparameterization, disentanglement, latent spaces
  2. 02
    Generative Adversarial NetworksAvailable
    training dynamics, mode collapse, StyleGAN, progressive training
  3. 03
    Normalizing FlowsAvailable
    change of variables, RealNVP, Glow, discrete flows
  4. 04
    Diffusion ModelsAvailable
    DDPM, score matching, classifier-free guidance, latent diffusion
  5. 05
    Autoregressive Generative ModelsAvailable
    PixelCNN, WaveNet, GPT as generative model
  6. 06
    Image & Video GenerationAvailable
    Stable Diffusion, DALL-E, Sora-style video, consistency models
  7. 07
    3D & Multimodal GenerationAvailable
    3D-aware generation, NeRF-based synthesis, any-to-any models
  8. 08
    Multimodal Foundation ModelsAvailable
    GPT-4V, Gemini, Flamingo — architectures that jointly process modalities
Part XI

AI Agents & Autonomous Systems

  1. 01
    Agent FundamentalsAvailable
    sense-plan-act loops, agent taxonomies, environments, PDDL, the OODA loop, what makes a system "agentic"
  2. 02
    LLM-Based AgentsAvailable
    ReAct, chain-of-thought, tool-augmented agents, cognitive architectures
  3. 03
    Planning & ReasoningAvailable
    tree-of-thought, MCTS, decomposition, verification, self-reflection
  4. 04
    Memory & Knowledge ManagementAvailable
    episodic, semantic, working memory — RAG vs. in-context vs. parametric
  5. 05
    Tool Use & Function CallingAvailable
    APIs, code execution, structured outputs, tool schema design, error handling
  6. 06
    Computer Use & GUI AgentsAvailable
    browser agents, OS-level control, visual action spaces, SWE-bench, WebArena
  7. 07
    Agent Frameworks & InfrastructureAvailable
    LangGraph, AutoGen, CrewAI, Claude Agent SDK, orchestration, observability
  8. 08
    Multi-Agent SystemsAvailable
    coordination, role specialization, debate, swarm behavior, emergent collaboration
  9. 09
    Agent Safety, Control & OversightAvailable
    prompt injection, sandboxing, minimal-footprint principle, HITL, corrigibility
  10. 10
    Agent Evaluation & BenchmarkingAvailable
    task success, GAIA, SWE-bench, WebArena, trajectory evaluation, safety metrics
  11. 11
    Using AI Agents: Getting StartedAvailable
    agent products, prompting agents, scoping tasks, verifying outputs, when not to use agents
  12. 12
    Building AI Agents: A Practitioner's HandbookAvailable
    framework selection, tool schemas, failure modes, evals, production deployment, monitoring
Part XII

Robotics & Embodied AI

  1. 01
    Robot Perception & SensingAvailable
    cameras, lidar, IMU fusion, SLAM, sensor calibration
  2. 02
    Motion Planning & ControlAvailable
    path planning, trajectory optimization, PID, model predictive control
  3. 03
    Learning from Demonstration & ImitationAvailable
    behavior cloning, DAgger, teleoperation datasets
  4. 04
    Sim-to-Real TransferAvailable
    domain randomization, physics simulators, gap mitigation
  5. 05
    Foundation Models for RoboticsAvailable
    RT-2, generalist manipulation policies, vision-language-action models
  6. 06
    Autonomous VehiclesAvailable
    perception stack, prediction, planning, safety, regulatory context
Part XIII

Specialized ML Methods

  1. 01
    Time Series Analysis & ForecastingAvailable
    ARIMA, exponential smoothing, temporal CNNs, Transformers for time series
  2. 02
    Anomaly DetectionAvailable
    statistical methods, isolation forest, autoencoders, contextual vs. collective anomalies
  3. 03
    Causal InferenceAvailable
    potential outcomes, DAGs, do-calculus, IV methods, difference-in-differences
  4. 04
    Causal Machine LearningAvailable
    causal discovery, uplift modeling, double ML, heterogeneous treatment effects
  5. 05
    Graph Neural NetworksAvailable
    message passing, GCN, GAT, GraphSAGE, heterogeneous graphs
  6. 06
    Survival Analysis & Event ModelingAvailable
    Kaplan-Meier, Cox regression, neural survival models
  7. 07
    Bayesian Deep LearningAvailable
    Bayesian neural nets, Monte Carlo dropout, deep GPs, Laplace approximation
  8. 08
    Meta-Learning & Few-Shot LearningAvailable
    MAML, prototypical networks, in-context learning as meta-learning
  9. 09
    Continual & Lifelong LearningAvailable
    catastrophic forgetting, EWC, progressive networks, replay methods
  10. 10
    Federated Learning & Privacy-Preserving MLAvailable
    federated averaging, differential privacy, secure aggregation
  11. 11
    Neurosymbolic AIAvailable
    logic plus learning, knowledge graphs, program synthesis, neuro-symbolic reasoning
Part XIV

Applied Domains

  1. 01
    Recommender SystemsAvailable
    collaborative filtering, content-based, matrix factorization, sequential recommendation
  2. 02
    Search & Information RetrievalAvailable
    BM25, dense retrieval, learning to rank, neural search
  3. 03
    Intro to Finance & EconomicsAvailable
    time value of money, risk & return, markets, EMH, asset classes, behavioural economics
  4. 04
    Financial ML & Quantitative MethodsAvailable
    alpha research, risk modeling, high-frequency, fraud detection
  5. 05
    Healthcare & Clinical AIAvailable
    medical imaging, EHR modeling, clinical NLP, trial design, regulatory considerations
  6. 06
    Intro to CybersecurityAvailable
    CIA triad, threat modelling, cryptography, network/endpoint/identity, attacks, SOC, governance
  7. 07
    AI for CybersecurityAvailable
    intrusion detection, malware classification, adversarial robustness in security contexts
  8. 08
    AI for Education & PersonalizationAvailable
    knowledge tracing, adaptive learning, intelligent tutoring
  9. 09
    AI for Manufacturing & OperationsAvailable
    predictive maintenance, quality control, supply chain optimization
  10. 10
    Human-AI Interaction & UXAvailable
    interface design, cognitive load, trust calibration, feedback collection
Part XV

AI for Science

  1. 01
    Scientific Machine LearningAvailable
    data-driven discovery, surrogate models, physics-informed networks, differentiable simulation
  2. 02
    Intro to ChemistryAvailable
    atoms, bonds, reactions, organic chemistry, spectroscopy, physical chemistry essentials
  3. 03
    Protein Science & AIAvailable
    amino acids, protein folding, AlphaFold, structure prediction & design, protein language models
  4. 04
    Biology, Genomics & AIAvailable
    central dogma, DNA sequencing, gene editing (CRISPR), single-cell biology, genome foundation models
  5. 05
    Pharmacology, Drug Discovery & AIAvailable
    drug discovery pipeline, drug-likeness, generative chemistry, molecular docking, clinical trials
  6. 06
    Climate, Earth Systems & AIAvailable
    atmosphere, oceans, carbon cycle, climate models, weather forecasting, climate emulators
  7. 07
    Physics & AIAvailable
    mechanics, electromagnetism, quantum theory, relativity, particle physics, fusion control
  8. 08
    Materials Science & AIAvailable
    crystals, material classes, defects, electronic structure, property prediction, autonomous labs
  9. 09
    Astronomy & Astrophysics & AIAvailable
    distance ladder, stellar evolution, cosmology, sky surveys, transient detection, exoplanets
  10. 10
    AI for MathematicsAvailable
    automated theorem proving, conjecture generation, symbolic regression, mathematical reasoning
Part XVI

MLOps & Production ML

  1. 01
    Experiment Tracking & ReproducibilityAvailable
    MLflow, W&B, DVC, determinism, environment management
  2. 02
    Feature Stores & Data Management for MLAvailable
    online/offline stores, point-in-time correctness, Feast, Tecton
  3. 03
    Model Deployment & ServingAvailable
    REST, gRPC, batch vs. real-time, model registries, containerization
  4. 04
    Model Monitoring & Drift DetectionAvailable
    data drift, concept drift, shadow deployment, alerting
  5. 05
    CI/CD for Machine LearningAvailable
    automated retraining, testing for ML, MLOps pipelines
  6. 06
    A/B Testing & Causal Experimentation in ProductionAvailable
    randomization, CUPED, multi-armed bandits
  7. 07
    Responsible Release & Deployment PracticesAvailable
    staged rollouts, kill switches, incident response, documentation
Part XVII

AI Infrastructure & Systems

  1. 01
    Hardware for MLAvailable
    GPUs, TPUs, NPUs, memory bandwidth, roofline model
  2. 02
    Distributed TrainingAvailable
    data parallelism, model parallelism, pipeline parallelism, ZeRO, FSDP
  3. 03
    Model CompressionAvailable
    pruning, quantization, knowledge distillation, structured vs. unstructured
  4. 04
    Inference OptimizationAvailable
    batching, KV caching, speculative decoding, FlashAttention, serving frameworks
  5. 05
    AI Chips & Custom SiliconAvailable
    ASIC design philosophy, photonics, neuromorphic computing, the competitive landscape
Part XVIII

AI Safety, Alignment & Governance

  1. 01
    AI Safety FundamentalsAvailable
    problem framing, threat models, instrumental convergence, Goodhart's law
  2. 02
    Technical Alignment MethodsAvailable
    scalable oversight, debate, amplification, interpretability-based approaches
  3. 03
    Robustness & Adversarial MLAvailable
    adversarial examples, certified defenses, distribution shift, red-teaming
  4. 04
    Mechanistic InterpretabilityAvailable
    circuits, features, superposition, probing, causal tracing
  5. 05
    Explainability for PractitionersAvailable
    SHAP, LIME, saliency maps, counterfactuals, when each method applies
  6. 06
    Fairness, Bias & EquityAvailable
    sources of bias, fairness definitions and tensions, auditing, mitigation
  7. 07
    Privacy in MLAvailable
    differential privacy, membership inference, model inversion, data deletion
  8. 08
    AI Governance, Policy & RegulationAvailable
    EU AI Act, executive orders, standards bodies, liability, international coordination

The compendium is a work in progress — chapters will land as they're written, and the table above will update with each release. If you have corrections, suggestions, or just want to tell me which chapter should be written next, you know where to find me.

— Alex