10-803 markov logic networks instructor: pedro domingos
TRANSCRIPT
![Page 1: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/1.jpg)
10-803Markov Logic Networks
Instructor:
Pedro Domingos
![Page 2: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/2.jpg)
Logistics
Instructor: Pedro Domingos Email: [email protected] Office: Wean 5317 Office hours: Thursdays 2:00-3:00
Course secretary: Sharon Cavlovich Web: http://www.cs.washington.edu/homes/
pedrod/803/ Mailing list: [email protected]
![Page 3: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/3.jpg)
Source Materials
Textbook:P. Domingos & D. Lowd,Markov Logic: An Interface Layer for AI, Morgan & Claypool, 2008
Papers Software:
Alchemy (alchemy.cs.washington.edu) MLNs, datasets, etc.:
Alchemy Web site
![Page 4: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/4.jpg)
Project
Possible projects: Apply MLNs to problem you’re interested in Develop new MLN algorithms Other
Key dates/deliverables: This week: Download Alchemy and start playing October 9 (preferably earlier): Project proposal November 6: Progress report December 4: Final report and short presentation Winter 2009: Conference submission (!)
![Page 5: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/5.jpg)
What Is Markov Logic?
A unified language for AI/ML Special cases:
First-order logic Probabilistic models
Syntax: Weighted first-order formulas Semantics: Templates for Markov nets Inference: Logical and probabilistic Learning: Statistical and ILP
![Page 6: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/6.jpg)
Why Take this Class?
Powerful set of conceptual tools New way to look at AI/ML
Powerful set of software tools* Increase your productivity Attempt more ambitious applications
Powerful platform for developing new learning and inference algorithms Many fascinating research problems
* Caveat: Not mature!
![Page 7: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/7.jpg)
Sample Applications
Information extraction Entity resolution Link prediction Collective classification Web mining Natural language
processing
Computational biology Social network analysis Robot mapping Activity recognition Personal assistants Probabilistic KBs Etc.
![Page 8: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/8.jpg)
Overview of the Class
Background Markov logic Inference Learning Extensions Your projects
![Page 9: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/9.jpg)
Background
Markov networks Representation Inference Learning
First-order logic Representation Inference Learning (a.k.a. inductive logic programming)
![Page 10: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/10.jpg)
Markov Logic
Representation Properties Relation to first-order logic and statistical
models Related approaches
![Page 11: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/11.jpg)
Inference
Basic MAP and conditional inference The MC-SAT algorithm Knowledge-based model construction Lazy inference Lifted inference
![Page 12: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/12.jpg)
Learning
Weight learning Generative Discriminative Incomplete data
Structure learning and theory revision Statistical predicate invention Transfer learning
![Page 13: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/13.jpg)
Extensions
Continuous domains Infinite domains Recursive MLNs Relational decision theory
![Page 14: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/14.jpg)
Your Projects
(TBA)
![Page 15: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/15.jpg)
Class begins here.
![Page 16: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/16.jpg)
AI: The First 100 Years
IQ HumanIntelligence
ArtificialIntelligence
1956 20562006
![Page 17: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/17.jpg)
AI: The First 100 Years
IQ HumanIntelligence
ArtificialIntelligence
1956 20562006
![Page 18: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/18.jpg)
AI: The First 100 Years
IQ HumanIntelligence
ArtificialIntelligence
1956 20562006
![Page 19: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/19.jpg)
The Interface Layer
Interface Layer
Applications
Infrastructure
![Page 20: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/20.jpg)
Networking
Interface Layer
Applications
Infrastructure
Internet
RoutersProtocols
WWWEmail
![Page 21: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/21.jpg)
Databases
Interface Layer
Applications
Infrastructure
Relational Model
QueryOptimization
TransactionManagement
ERP
OLTP
CRM
![Page 22: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/22.jpg)
Programming Systems
Interface Layer
Applications
Infrastructure
High-Level Languages
CompilersCodeOptimizers
Programming
![Page 23: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/23.jpg)
Hardware
Interface Layer
Applications
Infrastructure
VLSI Design
VLSI modules
Computer-Aided Chip Design
![Page 24: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/24.jpg)
Architecture
Interface Layer
Applications
Infrastructure
Microprocessors
BusesALUs
OperatingSystems
Compilers
![Page 25: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/25.jpg)
Operating Systems
Interface Layer
Applications
Infrastructure
Virtual machines
Hardware
Software
![Page 26: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/26.jpg)
Human-Computer Interaction
Interface Layer
Applications
Infrastructure
Graphical User Interfaces
Widget Toolkits
Productivity Suites
![Page 27: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/27.jpg)
Artificial Intelligence
Interface Layer
Applications
Infrastructure
Representation
Learning
Inference
NLP
Planning
Multi-AgentSystemsVision
Robotics
![Page 28: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/28.jpg)
Artificial Intelligence
Interface Layer
Applications
Infrastructure
Representation
Learning
Inference
NLP
Planning
Multi-AgentSystemsVision
Robotics
First-Order Logic?
![Page 29: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/29.jpg)
Artificial Intelligence
Interface Layer
Applications
Infrastructure
Representation
Learning
Inference
NLP
Planning
Multi-AgentSystemsVision
Robotics
Graphical Models?
![Page 30: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/30.jpg)
Logical and Statistical AI
Field Logical approach
Statistical approach
Knowledge representation
First-order logic Graphical models
Automated reasoning
Satisfiability testing
Markov chain Monte Carlo
Machine learning Inductive logic programming
Neural networks
Planning Classical planning
Markov decision processes
Natural language
processing
Definite clause grammars
Prob. context-free grammars
![Page 31: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/31.jpg)
We Need to Unify the Two
The real world is complex and uncertain Logic handles complexity Probability handles uncertainty
![Page 32: 10-803 Markov Logic Networks Instructor: Pedro Domingos](https://reader035.vdocuments.mx/reader035/viewer/2022062407/56649ce15503460f949abbec/html5/thumbnails/32.jpg)
Artificial Intelligence
Interface Layer
Applications
Infrastructure
Representation
Learning
Inference
NLP
Planning
Multi-AgentSystemsVision
Robotics
Markov Logic