Part V · 4 — Subject index and bibliography

draft

Where to find each topic in the Compendium, and the canonical sources that ground it.

Thematic subject index

Topic Where treated
Life cycle (11 steps) Part I
Real × formal × metaphor I/04
Mathematicssciencesinputs matrices I/03, V/02
Taxonomy (paradigmmodalityarchitecture) Part II
History of AI Part III
Transformer / attention IV/01 (LLM)
Diffusion / image generation IV/02
Vision (CNN/ViT) IV/03, IV/04
Audiospeechmusic/video IV/07–10
Sequences (RNN/SSM) IV/12, IV/13
Symbolic AI IV/15–18
Bayesian / classical ML IV/19–22
Evolutionary / swarm IV/23–25
Reinforcement learning IV/26–29
Alignment (RLHF/RLAIF) IV/29
Agents / RAG / neuro-symbolic IV/30–32
Recommendation / robotics IV/33, IV/34
Glossary V/01
Map of the sciences V/03

Bibliography — canonical references

Foundational works and milestones cited throughout the Compendium. A list of conceptual reference (verify edition/DOI on publication; prefer primary sources).

Fundamentals and theory

  • Turing, A. (1950). Computing Machinery and Intelligence.
  • Shannon, C. (1948). A Mathematical Theory of Communication.
  • McCulloch, W. & Pitts, W. (1943). *A Logical Calculus of Ideas Immanent in

    Nervous Activity.*

  • Pearl, J. (1988). Probabilistic Reasoning in Intelligent Systems.
  • Vapnik, V. (1995). The Nature of Statistical Learning Theory.

Deep learning and architectures

  • Rumelhart, Hinton & Williams (1986). *Learning representations by

    back-propagating errors.*

  • Krizhevsky, Sutskever & Hinton (2012). ImageNet Classification with Deep CNNs

    (AlexNet).

  • Vaswani et al. (2017). Attention Is All You Need (Transformer).
  • Ho, Jain & Abbeel (2020). Denoising Diffusion Probabilistic Models.
  • Kaplan et al. (2020). Scaling Laws for Neural Language Models.

Reinforcement learning and alignment

  • Mnih et al. (2015). Human-level control through deep RL (DQN).
  • Silver et al. (2017). Mastering the game of Go without human knowledge

    (AlphaZero).

  • Ouyang et al. (2022). Training language models to follow instructions

    (InstructGPT/RLHF).

  • Bai et al. (2022). Constitutional AI (Anthropic, RLAIF).

Reference works (textbooks)

  • Russell, S. & Norvig, P. Artificial Intelligence: A Modern Approach.
  • Goodfellow, Bengio & Courville. Deep Learning.
  • Bishop, C. Pattern Recognition and Machine Learning.
  • Sutton, R. & Barto, A. Reinforcement Learning: An Introduction.

Related internal material

  • The former volume IA_Volume_Completo was absorbed into this Compendium (Parts

    V–VI + state of the art) and retired — this Compendium is the reference document.

Credits and license

  • Language: pt-BR (per policies/language.kmd).
  • Illustrations: F-* briefs to be replaced by final art; for historical

    photos prefer public domain / Wikimedia (check the license on publication).

  • Status: draft (draft) — complete structure of the 5 parts; depth and art

    evolve by iteration.

End of Part V. With the appendices, the Artificial Intelligence Compendium closes its complete structure: life cycle (I), types in cards (II), history (III), encyclopedic chapters (IV) and reference (V).