Skip to main content

AI & Data Foundations

This branch contains compact course-style notes on machine learning, neural architectures, generative models, and data work. It is a reference shelf under cultivation, not a complete or neutral AI curriculum.

Current Branches

BranchCurrent strengthKnown gap
Machine Learningsupervised-learning vocabulary and classical modelscausal inference, uncertainty, calibration, decision theory, unsupervised/RL coverage
Deep Learningshort architecture maps from MLPs through transformers and diffusiontraining systems, scaling, alignment, robustness, multimodal and modern evaluation detail
Data Sciencedataset and workflow remindersgovernance, provenance, leakage, privacy, representativeness, and production quality

Agent runtimes, MCP, skills, tools, and harnesses belong in AI Systems. Current model/API choices belong in the dated Frontier Radar.

LLM Relevance, Not a New Validity Test

MaterialRelevance to LLMs now
probability, linear algebra, optimization, lossesstill foundational; scale does not remove their assumptions
MLPs and modern activationsdirectly relevant: Transformer FFNs commonly use GELU/SwiGLU rather than only textbook ReLU
CNNs and classic RNNsuseful contrasts and deployment alternatives, but not the usual text-LLM core
attention and Transformersdirectly relevant, including RoPE, GQA, RMSNorm, KV cache, and efficient kernels
VAE and diffusion notesadjacent generative foundations, not a sufficient explanation of text LLMs
leakage and evaluationessential: contamination and benchmark reuse get worse, not less important, at scale

This shelf still lacks focused foundations for tokenization/embeddings, pretraining data and objectives, scaling, instruction/preference post-training, open-ended generation evaluation, and inference systems. Do not infer those topics from older architecture pages; use the maintained AI Systems and Frontier notes until dedicated foundations exist.

How to Read the Legacy Notes

Most child pages are concise learning aids derived from a small number of textbooks or references. Their formulas and definitions can be useful, but brevity hides assumptions and competing schools. The branch has several biases:

  • textbook and architecture bias over deployment and sociotechnical context;
  • supervised-learning bias over causal, unsupervised, and sequential decision methods;
  • English-language and benchmark-dataset bias;
  • clean-data examples over shift, leakage, feedback, and operational failure;
  • historical sequence presented as a smooth progression rather than contested design choices.

Do not infer current state of the art from this branch.

Promotion Rule

A child note should move from compressed reference to maintained concept only when it is used. A substantive revision should add:

  1. the problem and assumptions, not only a definition;
  2. a derivation or executable example with observable behavior;
  3. failure modes, counterexamples, and comparisons;
  4. primary or authoritative sources plus provenance;
  5. links to mathematical prerequisites and practical evaluation;
  6. a clear distinction between durable theory and dated implementation.

Use Evidence and Bias in AI Notes as the review lens. This avoids mass-generating longer pages that remain shallow.

Supporting Network