AI Compendium · Part IV — Chapters by Type of AI

draft

The encyclopedic body of the Compendium. Each type of AI from the panel (Part II) gets a chapter that details it end to end — including the specialized life cycle (the 11 stages of Part I, now with the concrete details of the category).


The chapter template (8 sections)

Every chapter follows the same structure, so that the Compendium is consistent and comparable across types:

§ Section Content
1 Definition and short history What it is, in one page; lineage and milestones (links to Part III)
2 Foundations Sciences and mathematics specific to the type
3 Algorithms and architectures The machine on the inside: components, variants, key formulas
4 Inputs Hardware, data, data structures, systems/MLOps
5 Specialized life cycle The 11 stages (Part I) applied to this type
6 Capabilities, modes and modalities What it can do; types of intelligence covered
7 Limits, risks and ethics Failures, biases, cost, alignment; [metaphor] vs. mechanism
8 State of the art and examples Real systems; frontier trends

Size rule: a chapter starts as a single file NN-slug.kmd. When it grows beyond what is comfortable to read/edit, it is promoted to a directory NN-slug/ with the 8 sections in numbered docs (same pattern as Part I).


Chapter index (card → chapter map)

Organized by paradigm (Level 1 of the taxonomy). Each chapter corresponds to a card from Part II.

Connectionist (Deep Learning)

Ch. Type Doc Status
01 LLM 01-llm.kmd pilot ✅
02 Diffusion Model 02-diffusion.kmd
03 CNN (vision) 03-cnn.kmd
04 Vision Transformer 04-vit.kmd
05 GAN 05-gan.kmd
06 VAE 06-vae.kmd
07 ASR (speech→text) 07-asr.kmd
08 TTS (voice synthesis) 08-tts.kmd
09 Music Model 09-music.kmd
10 Video Model 10-video.kmd
11 GNN 11-gnn.kmd
12 RNN / LSTM 12-rnn.kmd
13 SSM / Mamba 13-ssm.kmd
14 Unified Multimodal 14-multimodal.kmd

Symbolic

Ch. Type Doc Status
15 Expert System 15-expert-system.kmd
16 Planning and Search 16-planning.kmd
17 Knowledge Graph + Reasoner 17-knowledge-graph.kmd
18 Logic Programming / Solvers 18-solvers.kmd

Probabilistic / Bayesian

Ch. Type Doc Status
19 Bayesian Network 19-bayesian-network.kmd
20 HMM 20-hmm.kmd
21 Gaussian Process 21-gaussian-process.kmd
22 Classical ML (treesboostingSVM) 22-classical-ml.kmd
35 Markov Chain / n-gram LM 35-markov-chain.kmd

Evolutionary

Ch. Type Doc Status
23 Genetic Algorithm 23-genetic-algorithm.kmd
24 Neuroevolution 24-neuroevolution.kmd
25 Swarm Intelligence 25-swarm.kmd

Reinforcement

Ch. Type Doc Status
26 Deep RL (value) 26-deep-rl-value.kmd
27 Policy RL / AlphaZero 27-alphazero.kmd
28 Continuous RL / Control 28-rl-control.kmd
29 RLHF / RLAIF 29-rlhf.kmd

Hybrid / Neuro-symbolic

Ch. Type Doc Status
30 Agent (Agentic AI) 30-agent.kmd
31 RAG 31-rag.kmd
32 Neuro-symbolic 32-neuro-symbolic.kmd
33 Recommendation System 33-recommendation.kmd
34 Embodied Robotics 34-robotics.kmd

34 chapters, one per card, plus ch. 35 (Markov Chain / n-gram LM) — the memoryless ancestor of the language model, added under the Probabilistic paradigm. The LLM pilot chapter fixes the template; the others follow it. Gaps in the taxonomy (intersections not covered in the panel) may become extra chapters numbered in sequence.