32
10-803 Markov Logic Networks Instructor: Pedro Domingos
| Date post: | 16-Dec-2015 |
| Category: |
Documents |
| Upload: | brittany-small |
| View: | 223 times |
| Download: | 3 times |
10-803Markov Logic Networks
Instructor:
Pedro Domingos
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]
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
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 (!)
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
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!
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.
Overview of the Class
Background Markov logic Inference Learning Extensions Your projects
Background
Markov networks Representation Inference Learning
First-order logic Representation Inference Learning (a.k.a. inductive logic programming)
Markov Logic
Representation Properties Relation to first-order logic and statistical
models Related approaches
Inference
Basic MAP and conditional inference The MC-SAT algorithm Knowledge-based model construction Lazy inference Lifted inference
Learning
Weight learning Generative Discriminative Incomplete data
Structure learning and theory revision Statistical predicate invention Transfer learning
Extensions
Continuous domains Infinite domains Recursive MLNs Relational decision theory
Your Projects
(TBA)
Class begins here.
AI: The First 100 Years
IQ HumanIntelligence
ArtificialIntelligence
1956 20562006
AI: The First 100 Years
IQ HumanIntelligence
ArtificialIntelligence
1956 20562006
AI: The First 100 Years
IQ HumanIntelligence
ArtificialIntelligence
1956 20562006
The Interface Layer
Interface Layer
Applications
Infrastructure
Networking
Interface Layer
Applications
Infrastructure
Internet
RoutersProtocols
WWWEmail
Databases
Interface Layer
Applications
Infrastructure
Relational Model
QueryOptimization
TransactionManagement
ERP
OLTP
CRM
Programming Systems
Interface Layer
Applications
Infrastructure
High-Level Languages
CompilersCodeOptimizers
Programming
Hardware
Interface Layer
Applications
Infrastructure
VLSI Design
VLSI modules
Computer-Aided Chip Design
Architecture
Interface Layer
Applications
Infrastructure
Microprocessors
BusesALUs
OperatingSystems
Compilers
Operating Systems
Interface Layer
Applications
Infrastructure
Virtual machines
Hardware
Software
Human-Computer Interaction
Interface Layer
Applications
Infrastructure
Graphical User Interfaces
Widget Toolkits
Productivity Suites
Artificial Intelligence
Interface Layer
Applications
Infrastructure
Representation
Learning
Inference
NLP
Planning
Multi-AgentSystemsVision
Robotics
Artificial Intelligence
Interface Layer
Applications
Infrastructure
Representation
Learning
Inference
NLP
Planning
Multi-AgentSystemsVision
Robotics
First-Order Logic?
Artificial Intelligence
Interface Layer
Applications
Infrastructure
Representation
Learning
Inference
NLP
Planning
Multi-AgentSystemsVision
Robotics
Graphical Models?
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
We Need to Unify the Two
The real world is complex and uncertain Logic handles complexity Probability handles uncertainty
Artificial Intelligence
Interface Layer
Applications
Infrastructure
Representation
Learning
Inference
NLP
Planning
Multi-AgentSystemsVision
Robotics
Markov Logic
![Real-time collective entity resolution · Domingos proposed a solution to the entity resolution problem based on Markov logic [2]. Their work combines first-order logic and probabilistic](https://static.documents.pub/doc/80x56/5fbbfb6988071625622c1526/real-time-collective-entity-resolution-domingos-proposed-a-solution-to-the-entity.jpg)
![Integrating Knowledge and Reasoning in Image Understanding · I Markov Logic Network. MLN ([Richardson and Domingos, 2006]) is a popular framework that uses weighted First Order Logical](https://static.documents.pub/doc/80x56/5fbbfa97584b3969ec482474/integrating-knowledge-and-reasoning-in-image-understanding-i-markov-logic-network.jpg)
