Nonparametric Bayesian times series models: infinite HMMs and beyond
1 hour 7 mins 46 secs,
399.94 MB,
Flash Video
480x360,
25.0 fps,
44100 Hz,
805.78 kbits/sec
Share this media item:
Embed this media item:
Embed this media item:
About this item
Description: |
Ghahramani, Z (Cambridge)
Friday 20 June 2008, 16:10-17:10 Inference and Estimation in Probabilistic Time-Series Models |
---|
Created: | 2008-06-27 17:27 | ||
---|---|---|---|
Collection: | Statistical Theory and Methods for Complex, High-Dimensional Data | ||
Publisher: | Isaac Newton Institute | ||
Copyright: | Ghahramani, Z | ||
Language: | eng (English) | ||
Distribution: | World (downloadable) | ||
Credits: |
|
||
Explicit content: | No | ||
Aspect Ratio: | 4:3 | ||
Screencast: | No | ||
Bumper: | /sms-ingest/static/new-4x3-bumper.dv | ||
Trailer: | /sms-ingest/static/new-4x3-trailer.dv |
Abstract: | Hidden Markov models (HMMs) are one of the most widely used statistical models for time series. Traditionally, HMMs have a known structure with a fixed number of states and are trained using maximum likelihood techniques. The infinite HMM (iHMM) allows a potentially unbounded number of hidden states, letting the model use as many states as it needs for the data (Beal, Ghahramani and Rasmussen 2002). Teh, Jordan, Beal and Blei (2006) showed that a form of the iHMM could be derived from the Hierarchical Dirichlet Process, and described a Gibbs sampling algorithm based on this for the iHMM. I will talk about recent work we have done on infinite HMMs. In particular: we now have a much more efficient inference algorithm based on dynamic programming, called 'Beam Sampling', which should make it possible to apply iHMMs to larger problems. We have also developed a factorial version of the iHMM which makes it possible to have an unbounded number of binary state variables, and can be thought of as a time-series generalization of the Indian buffet process.
Joint work with Jurgen van Gael (Cambridge), Yunus Saatci (Cambridge) and Yee Whye Teh (Gatsby Unit, UCL). Related Links * http://learning.eng.cam.ac.uk/zoubin/ - Web homepage |
---|
Available Formats
Format | Quality | Bitrate | Size | |||
---|---|---|---|---|---|---|
MPEG-4 Video | 480x360 | 1.84 Mbits/sec | 935.90 MB | View | Download | |
WebM | 480x360 | 643.29 kbits/sec | 315.68 MB | View | Download | |
Flash Video * | 480x360 | 805.78 kbits/sec | 399.94 MB | View | Download | |
iPod Video | 480x360 | 505.23 kbits/sec | 250.77 MB | View | Download | |
QuickTime | 384x288 | 848.48 kbits/sec | 421.13 MB | View | Download | |
MP3 | 44100 Hz | 125.0 kbits/sec | 61.83 MB | Listen | Download | |
Auto | (Allows browser to choose a format it supports) |