Transformers & Foundation Models · Artificial Intelligence & Systems · Brain Knowledge Library

SUBJECT ARCHIVEARTIFICIAL INTELLIGENCE & SYSTEMS

1 Canonical Notebook

Transformers & Foundation Models

Technical study notebooks detailing self-attention, transformer encoder-decoder blocks, tokenization, RoPE positional encodings, and scaling laws.

Read Primary Notebook →

Canonical MDX Notebooks

The core knowledge artifacts: comprehensive, proof-backed, and verified study notebooks.

1 Document

v1.0.0Updated 2026-10-05

Scaled Dot-Product Attention & Transformer Architectures

Focus: Personal Notes

Mathematical mechanics of Scaled Dot-Product Attention, Multi-Head Attention, Positional Encodings, and Transformer encoder-decoder topologies.

#AI#Transformers#Self-Attention#Deep-Learning#Multi-Head#Positional-Encoding

Read Notebook →

🖨 Print / PDF

Examination Preparation & Practice Bank

High-Scoring Model Answers

Every canonical notebook includes an embedded Question Bank featuring solved examination questions, mark breakdowns, step-by-step arithmetic proofs, and active recall flashcards.

Q&A: Scaled... →