Manolis Kellis
@manoliskellis1·24.9K subscribers·255 videos
MIT CompBio Lecture 05 - HMMs II
Posted
October 3, 2018
Views
2,577
Likes
17
Comments
1
Engagement
0.70%
October 3, 2018
2,577
17
1
0.70%
Every word spoken in this episode is indexed. Type any phrase to jump straight to the moment it was said.
Type any word or phrase that may have been spoken. Click a result to seek the player to that exact moment.
Try a name, a topic, or a quoted line
See what was published immediately before and after this episode.
1:17:18Now PlayingMIT Computational Biology: Genomes, Networks, Evolution, Health
Prof. Manolis Kellis
Fall 2018
Lecture 05 - Hidden Markov Models - Part II
1. Review: Basics and four algorithms from last time
- Markov Chains and Hidden Markov Models
- Calculating likelihoods P(x,π) (algorithm 1)
- Viterbi algorithm: Find π* = argmaxπ P(x,π) (alg 3)
- Forward algorithm: Find P(x), over all paths (alg 2)
- Posterior Decoding: Find most likely π_i, all paths (alg 4)
2. Increasing the state space / adding memory
- Finding GC-rich regions vs. finding CpG islands
- Gene structures GENSCAN, chromatin ChromHMM
3. Learning (ML training, Baum-Welch, Viterbi training)
- Supervised: Find e_i(.) and a_ij given labeled sequence
- Unsupervised: given only x, infer annotation + params
4. Conditional Random Fields (CRFs) & dependencies
Slides for Lecture 5:
Sentinel Indexing in Progress
Metadata and chapters are available. Claim extraction for this episode is pending.
All video content is delivered via YouTube embedded players in accordance with the YouTube Terms of Service. Sentinel provides research tools that promote discovery and accountability across political media.
