0.25
0.5
0.75
1.25
1.5
1.75
2
On the Completeness of First-Order Knowledge Compilation for Lifted Probabilistic Inference
Published on Jan 25, 20124698 Views
Probabilistic logics are receiving a lot of attention today because of their expressive power for knowledge representation and learning. However, this expressivity is detrimental to the tractability o
Related categories
Chapter list
On the Completeness of First-Order Knowledge Compilation for Lifted Probabilistic Inference00:00
Outline00:05
Outline: Probabilistic Logic00:30
First-Order Logic00:32
Probabilistic Logic01:24
Lifted Probabilistic Inference02:29
Questions?03:30
Outline: Lifted Inference04:30
Lifted Inference by First-Order Knowledge Compilation - 104:39
Weighted First-Order Model Counting - 105:37
Weighted First-Order Model Counting - 206:08
Weighted First-Order Model Counting - 306:32
Weighted First-Order Model Counting - 406:47
Lifted Inference by First-Order Knowledge Compilation - 206:59
Lifted Inference by First-Order Knowledge Compilation - 307:02
Lifted Inference by First-Order Knowledge Compilation - 407:06
Lifted Inference by First-Order Knowledge Compilation - 507:19
Lifted Inference by First-Order Knowledge Compilation - 608:05
Lifted Inference by First-Order Knowledge Compilation - 708:21
Outline: Compilation Algorithm08:45
Compilation Algorithm CR1 - 109:07
Compilation Algorithm CR1 - 210:00
New Rule: Domain Recursion - 110:15
New Rule: Domain Recursion - 211:04
New Rule: Domain Recursion - 311:10
New Rule: Domain Recursion - 411:14
Experiments11:40
Outline. Completeness12:14
Domain-Lifted Probabilistic Inference12:26
Completeness13:34
Completeness of CR1 and CR214:24
Importance of Completeness Results15:36
Outline: Conclusions16:27
Conclusions16:30
Poster!17:11