Statistical Relational Learning: Review and Recent Advances
Duration: 31 mins 46 secs
Share this media item:
Embed this media item:
Embed this media item:
About this item
| Description: |
Getoor, L (University of California, Santa Cruz)
Monday 25th July 2016 - 15:30 to 16:00 |
|---|
| Created: | 2016-07-28 14:56 |
|---|---|
| Collection: | Theoretical Foundations for Statistical Network Analysis |
| Publisher: | Isaac Newton Institute |
| Copyright: | Getoor, L |
| Language: | eng (English) |
| Distribution: |
World
(downloadable)
|
| Explicit content: | No |
| Aspect Ratio: | 16:9 |
| Screencast: | No |
| Bumper: | UCS Default |
| Trailer: | UCS Default |
| Abstract: | Statistical relational learning (SRL) is a subfield of machine learning that combines relational representations (from databases and AI) with probabilistic modeling techniques (most often graphical models)for modeling network data (typically richly structured multi-relational and multi-model networks). In this talk, I will briefly review some SRL modeling techniques, and then I will introduce hinge-loss Markov random fields (HL-MRFs), a new kind of probabilistic graphical model that supports scalable collective inference from richly structured data. HL-MRFs unify three different approaches to convex inference: LP approximations for randomized algorithms, local relaxations for probabilistic graphical models, and inference in soft logic. I will show that all three lead to the same inference objective. This makes inference in HL-MRFs highly scalable. Along the way, I will describe several successful applications of HL-MRFs and I will describe probabilistic soft logic, a declarative language for defining HL-MRFS. |
|---|---|
Available Formats
| Format | Quality | Bitrate | Size | |||
|---|---|---|---|---|---|---|
| MPEG-4 Video | 640x360 | 1.94 Mbits/sec | 462.71 MB | View | Download | |
| WebM | 640x360 | 679.14 kbits/sec | 158.10 MB | View | Download | |
| iPod Video | 480x270 | 522.24 kbits/sec | 121.51 MB | View | Download | |
| MP3 | 44100 Hz | 249.79 kbits/sec | 58.18 MB | Listen | Download | |
| Auto * | (Allows browser to choose a format it supports) | |||||