This preview shows page 1. Sign up to view the full content.
Unformatted text preview: ve binomial distribution”:
0.08 0.06 0.04 0.02 0
Prof. Jeﬀ Bilmes 10 20 30 40 50 60 d
EE596A/Winter 2013/DGMs – Lecture 4  Jan 23rd, 2013 page 472 (of 239) HMMs HMMs as GMs Other HMM queries What HMMs can do MPE Summ State Duration Modeling
If we have multiple parallel states in series, all of which share the
same observation distribution, we can construct much more
interesting (multimodal) distributions. Prof. Jeﬀ Bilmes EE596A/Winter 2013/DGMs – Lecture 4  Jan 23rd, 2013 page 473 (of 239) HMMs HMMs as GMs Other HMM queries What HMMs can do MPE Summ State Duration Modeling
If we have multiple parallel states in series, all of which share the
same observation distribution, we can construct much more
interesting (multimodal) distributions.
For example, the following left chain will have distribution as shown
on the right (a mixture of negative binomial distributions). Prof. Jeﬀ Bilmes EE596A/Winter 2013/DGMs – Lecture 4  Jan 23rd, 2013 page 473 (of 239) HMMs HMMs as GMs Other HMM queries What HMMs can do MPE Summ State Duration Modeling
If we have multiple parallel states in series, all of which share the
same observation distribution, we can construct much more
interesting (multimodal) distributions.
For example, the following left chain will have distribution as shown
on the right (a mixture of negative binomial distributions). Prof. Jeﬀ Bilmes EE596A/Winter 2013/DGMs – Lecture 4  Jan 23rd, 2013 page 473 (of 239) HMMs HMMs as GMs Other HMM queries What HMMs can do MPE Summ State Duration Modeling
If we have multiple parallel states in series, all of which share the
same observation distribution, we can construct much more
interesting (multimodal) distributions.
For example, the following left chain will have distribution as shown
on the right (a mixture of negative binomial distributions).
0.6 0.6
0.4 0.6 0.6 0.4 0.4
0.4 0.2
0.99
0.8 Prof. Jeﬀ Bilmes 0.99
0.01 0.99
0.01 0.99
0.01 0.01 EE596A/Winter 2013/DGMs – Lecture 4  Jan 23rd, 2013 page 473 (of 239) HMMs HMMs as GMs Other HMM queries What HMMs can do MPE Summ State Duration Modeling
If we have multiple parallel states in series, all of which share the
same observation distribution, we can construct much more
interesting (multimodal) distributions.
For example, the following left chain will have distribution as shown
on the right (a mixture of negative binomial distributions).
0.025
0.6 0.6
0.4 0.6 0.6 0.4 0.02 0.4
0.4 0.2
0.99
0.8 0.99
0.01 0.99
0.01 0.015 0.99
0.01 0.01 0.01 0.005 Prof. Jeﬀ Bilmes 10 20 30
d EE596A/Winter 2013/DGMs – Lecture 4  Jan 23rd, 2013 40 50 60 page 473 (of 239) HMMs HMMs as GMs Other HMM queries What HMMs can do MPE Summ State Duration Modeling
If we have multiple parallel states in series, all of which share the
same observation distribution, we can construct much more
interesting (multimodal) distributions.
For example, the following left chain will have distribution as shown
on the right (a mixture of negative binomial distributions).
0.025...
View
Full
Document
 Winter '14

Click to edit the document details