CHAPTER 26 / 40
Probabilistic Graphical Models
4 lessons · Explore, experiment and understand.
DOJO PETYour little coding companion
DOJO / YOUR GUIDE
Let’s figure it out.
Ask me about this course or where to start.
Chapter lessons
4 lessons
- Step 112~10m1Code · 12
Bayesian Networks
A Bayesian network factorizes a giant joint distribution into a directed graph of small conditional tables — turning an exponential problem…
Open lesson - Step 113~5m1Code · 11
Markov Random Fields
When relationships are symmetric rather than causal, an undirected graph with potential functions — a Markov random field — is the right mod…
Open lesson - Step 114~5m1Code · 11
Exact Inference: Variable Elimination & Belief Propagation
Naively summing out variables is exponential; variable elimination pushes sums inside products, and belief propagation passes local messages…
Open lesson - Step 115~5m1Code · 11
Hidden Markov Models & the Forward Algorithm
An HMM is a Bayesian network unrolled in time: hidden states emit observations. The forward algorithm is belief propagation on that chain, s…
Open lesson