Eewashingtonedubilmes classesee596awinter2013 uid

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: p://j.ee.washington.edu/~bilmes/ classes/ee596a_winter_2013/). uid is this class name (lower case) and pwd are the quarter/year of the class. Prof. Jeff Bilmes EE596A/Winter 2013/DGMs – Lecture 4 - Jan 23rd, 2013 page 4-4 (of 239) Logistics Review Relevant Readings: Readings/handouts Readings are in a sub-directory “reading drafts” directly below our web page (http://j.ee.washington.edu/~bilmes/ classes/ee596a_winter_2013/). uid is this class name (lower case) and pwd are the quarter/year of the class. Note, the PDF file is password protected. Send me email if you have trouble (adobe reader should have no problems reading it). Prof. Jeff Bilmes EE596A/Winter 2013/DGMs – Lecture 4 - Jan 23rd, 2013 page 4-4 (of 239) Logistics Review Cumulative Outstanding Reading Read 8.1 - 8.3 in “doc.pdf” Read HMM section in readings. Prof. Jeff Bilmes EE596A/Winter 2013/DGMs – Lecture 4 - Jan 23rd, 2013 page 4-5 (of 239) Logistics Review Review section - reminder All slides in this section are either from previous lectures, or are a summary of material from previous lectures. Prof. Jeff Bilmes EE596A/Winter 2013/DGMs – Lecture 4 - Jan 23rd, 2013 page 4-6 (of 239) Logistics Review Review section - reminder All slides in this section are either from previous lectures, or are a summary of material from previous lectures. For more details, see the previous lectures. Prof. Jeff Bilmes EE596A/Winter 2013/DGMs – Lecture 4 - Jan 23rd, 2013 page 4-6 (of 239) Logistics Review Review - Markov chains Markov chains - the “hidden” chain in HMMs. Prof. Jeff Bilmes EE596A/Winter 2013/DGMs – Lecture 4 - Jan 23rd, 2013 page 4-7 (of 239) Logistics Review Review - Markov chains Markov chains - the “hidden” chain in HMMs. Critical to understand Markov chains in order to understand HMMs. Prof. Jeff Bilmes EE596A/Winter 2013/DGMs – Lecture 4 - Jan 23rd, 2013 page 4-7 (of 239) Logistics Review Review - Hidden Markov Models Many views of HMMs (see readings), including 1) random functions of Markov chains, 2) exponentially sized mixture distributions, 3) generative process Balls/Urns, 4) set of 2T r.v.s with conditional independence statements, 5) as a distribution over 2T variables with factorization properties; 6) graphical model (a particular tree); and others (see readings for unaries + smoothing). Prof. Jeff Bilmes EE596A/Winter 2013/DGMs – Lecture 4 - Jan 23rd, 2013 page 4-8 (of 239) Logistics Review Review - Hidden Markov Models Many views of HMMs (see readings), including 1) random functions of Markov chains, 2) exponentially sized mixture distributions, 3) generative process Balls/Urns, 4) set of 2T r.v.s with conditional independence statements, 5) as a distribution over 2T variables with factorization properties; 6) graphical model (a particular tree); and others (see readings for unaries + smoothing). Typically homogeneous (fininite number of parameters for any expansion) Prof. Jeff Bilmes EE596A/Winter 2013/DGMs – Lecture 4 - Jan 23rd, 2013 page 4-8 (of 239) Logistics Review HMM Forward Recursion This yields, p(x1:t , qt ) = p(x1:t...
View Full Document

Ask a homework question - tutors are online