Deep Gaussian Process Priors for Bayesian Inverse Problems
37 mins 32 secs,
140.33 MB,
WebM
640x360,
29.97 fps,
44100 Hz,
510.48 kbits/sec
Share this media item:
Embed this media item:
Embed this media item:
About this item
| Description: |
Teckentrup, A
Thursday 12th April 2018 - 11:30 to 12:00 |
|---|
| Created: | 2018-04-13 15:22 |
|---|---|
| Collection: | Uncertainty quantification for complex systems: theory and methodologies |
| Publisher: | Isaac Newton Institute |
| Copyright: | Teckentrup, A |
| Language: | eng (English) |
| Distribution: |
World
(downloadable)
|
| Explicit content: | No |
| Aspect Ratio: | 16:9 |
| Screencast: | No |
| Bumper: | UCS Default |
| Trailer: | UCS Default |
| Abstract: | Co-authors: Matt Dunlop (Caltech), Mark Girolami (Imperial College), Andrew Stuart (Caltech)
Deep Gaussian processes have received a great deal of attention in the last couple of years, due to their ability to model very complex behaviour. In this talk, we present a general framework for constructing deep Gaussian processes, and provide a mathematical argument for why the depth of the processes is in most cases finite. We also present some numerical experiments, where deep Gaussian processes have been employed as prior distributions in Bayesian inverse problems. Related Links https://arxiv.org/abs/1711.11280 - Preprint |
|---|---|
Available Formats
| Format | Quality | Bitrate | Size | |||
|---|---|---|---|---|---|---|
| MPEG-4 Video | 640x360 | 1.94 Mbits/sec | 546.26 MB | View | Download | |
| WebM * | 640x360 | 510.48 kbits/sec | 140.33 MB | View | Download | |
| iPod Video | 480x270 | 522.04 kbits/sec | 143.45 MB | View | Download | |
| MP3 | 44100 Hz | 249.78 kbits/sec | 68.70 MB | Listen | Download | |
| Auto | (Allows browser to choose a format it supports) | |||||