Learning Path 02

Models From First Principles

Understand how learned systems are assembled from reusable components, scorers, policies, hierarchies and compact reasoning architectures.

Move one level above framework mechanics and study the structures that turn learned components into complete models.

Model Architecture 9 chapters Sequential or reference
Start at chapter 00 Use with AI
Complete curriculum

Chapters

Work through the path in order, or jump directly to the mechanism you need.

  1. 00The Model Inside the Model
  2. 01MR.Q — Building a Neural Quality Model From Two Embeddings
  3. 02EBT — From One Score to Q, V, Policy and Advantage
  4. 03SICQL — Building a Model From Q, V and Policy Networks
  5. 04HRM — Hierarchical Reasoning With Fast and Slow Recurrent State
  6. 05Tiny — Recursive Reasoning With a Small Neural Network
  7. 06Inside Tiny — Residual Blocks, Attention and Sparse Autoencoders
  8. 07PACS — Building an Optimizer From Gradient Statistics
  9. 08Which Model Should You Use? MR.Q, EBT, SICQL, HRM, Tiny and PACS Compared