“Know how to solve every problem that has been solved.” “What I cannot create, I do not understand.” — Richard Feynman

Statistics & Inference

Courses

Probability, estimation, and how to reason from data to model.

7 skills 0 questions ← whole tech tree

Content for this course is still being written. For now, explore the skill map below — every node links to its full page.

Skill map

Each node is a skill; an arrow means "learn this first." Deep-dive links go to the full pages.

Bayes' Rule…

Prior × likelihood ÷ evidence = posterior.

content coming soon
deep dive ↓Bayes' Rule
Intractable Likelihoods…

When the likelihood hides in latent simulator paths.

content coming soon
deep dive ↓Why Some Likelihoods Can't Be Written Down
ABC…

Bayes by Monte Carlo: accept when output matches.

content coming soon
deep dive ↓ABC: Bayes by Monte Carlo
Where ABC Breaks…

Curse of dimensionality and wasted simulations.

content coming soon
deep dive ↓Where ABC Breaks
Normalizing Flows…

Invertible maps learn flexible conditional densities.

content coming soon
deep dive ↓Normalizing Flows
Neural Posterior Estimation…

Amortize the posterior across observations with a network.

content coming soon
deep dive ↓Neural Posterior Estimation
Path-Integral Frame…

Every SBI method approximates the same latent integral.

content coming soon
deep dive ↓The Path-Integral Frame