Opening Probabilistic Inference II
Probabilistic Inference II
- Length
- 49 min
- Level
- Undergraduate
- Recorded
- MIT2014
Chapter 1 of 8: Before the lecture
Winston classifies coins and political parties with naive Bayes, then scores rival network structures to discover one.
Bayesian inference networks in Winston's MIT 6.034 session start from conditional independence and the chain rule, which turn a joint distribution into a product of conditional probabilities. Winston simulates data through a network and counts tallies to fill its probability tables. Naive Bayesian classification follows, applied to identifying a coin from its flips and a voter's party from their record. He then scores competing network structures, using log probabilities to avoid underflow and random restarts to search the space of topologies. Medical diagnosis, lie detectors and software debugging close the session; basic probability and conditional probability are assumed.
Bayesian inference networks in Winston's MIT 6.034 session start from conditional independence and the chain rule, which turn a joint distribution into a product of conditional probabilities. Winston simulates data through a network and counts tallies to fill its probability tables. Naive Bayesian classification follows, applied to identifying a coin from its flips and a voter's party from their record. He then scores competing network structures, using log probabilities to avoid underflow and random restarts to search the space of topologies. Medical diagnosis, lie detectors and software debugging close the session; basic probability and conditional probability are assumed.

This lecture
Lecture 22 of 27 of Artificial Intelligence.
Choose a node to see how it connects to this lecture. What comes before is on the leftat the top. What comes after is on the rightat the bottom. The ring is what it teaches. People and places are above. Other lectures and books are below.
Press a chosen node again to open it.
Your comment is kept while you sign up.Sign in