|
CSE 574 - Artificial Intelligence II - Autumn 2011 |
|
 CSE Home |
About Us |
Search |
Contact Info |
|
Instructor: Pedro Domingos
Office hours: Wednesdays 3:00-3:50 p.m., CSE 648 |
TA: Aniruddh Nath Office hours: Mondays 3:00-3:50 p.m., CSE 216 |
Class meets:
Mondays, Wednesdays 1:30-2:50 p.m. in CSE 203
| Date | Topics & Slides | Readings | Project |
|---|---|---|---|
| Sept. 28 | Introduction | Chapter 1 | - |
| Oct. 3 | Markov networks | Section 2.2 | - |
| Oct. 5 | First-order logic and inductive logic programming | Section 2.1 | - |
| Oct. 10 | Markov logic and other SRL approaches | Sections 2.3 and 2.4 | - |
| Oct. 12 | Markov logic (contd.) | Sections 2.3 and 2.4 | - |
| Oct. 17 | Applications of Markov logic | Chapter 6, Alchemy tutorial | - |
| Oct. 19 | Applications of Markov logic (contd.) | Chapter 6, Alchemy tutorial | Proposals due | Oct. 24 | Applications of Markov logic (contd.) | Chapter 6, Alchemy tutorial | - |
| Oct. 26 | Applications of Markov logic (contd.) | Chapter 6, Alchemy tutorial | - |
| Oct. 31 | Inference | Chapter 3 | - |
| Nov. 2 | Inference (contd.) | Chapter 3 | - |
| Nov. 7 | Weight learning | Section 4.1 | - |
| Nov. 9 | Structure learning | Sections 4.2, 4.3 and 4.4 | - |
| Nov. 14 |
Probabilistic
Theorem Proving (Chloé) Coarse-to-Fine Inference and Learning for First-Order Probabilistic Models (Austin) |
- | - |
| Nov. 16 |
Tuffy: Scaling up Statistical Inference in
Markov Logic Networks Using an RDBMS (Emad) Scaling Textual Inference to the Web (Cullen) Approximate Inference for Planning in Stochastic Relational Worlds (Igor) |
- | Progress reports due |
| Nov. 21 |
Hybrid Markov Logic Networks (Abe) Recognizing Multi-Agent Activities from GPS Data (Kathleen) Probabilistic Event Logic for Interval-Based Event Recognition (Kevin) |
- | - |
| Nov. 23 |
Event Modeling and Recognition Using Markov Logic Networks
(Jinna) Collective Semantic Role Labelling with Markov Logic (To) Automatically Refining the Wikipedia Infobox Ontology (Sai) |
- | - |
| Nov. 28 |
Relational Reinforcement Learning (Svet) Policy Transfer via Markov Logic Networks (Yanping) Modelling Relational Data Using Bayesian Clustered Tensor Factorization (Rob) |
- | - |
| Nov. 30 |
Joint Unsupervised Coreference Resolution with Markov Logic
(Congle) Unsupervised Semantic Parsing (Conrad) |
- | - |
| Dec. 5 |
Semantic Role Labeling for English Using Markov Logic (To) Scale up Data Curation with MLN approach (Emad) Information Extraction from US Bankruptcy Petition Forms (Yanping) Markov Logic for Inverse Reinforcement Learning (Svet) Picard (Kathleen) |
- | - |
| Dec. 7 |
Modelling Character Sequences with Sum-Product Networks (Rob & Igor) Coarse-to-Fine Variational Inference (Chloé) Unifying Automated Software Bug Localization with Markov Logics (Sai & Congle) Kinect-based Activity Recognition Using Markov Logic Networks (Kevin & Jinna) Hierarchical Clustering Using Markov Logic Networks (Abe) |
- | - |
| Dec. 14 | - | - | Final reports due |
Students will do a project and give a seminar. Projects can be done individually or in groups of two, and are due on December 14. Seminars are done individually, and are Pass/Fail; a Pass is required to complete the class. The class grade will be the project grade. An ideal project is applying statistical relational learning (SRL) to your area of research, or developing a new SRL algorithm. You can also propose any other project related to SRL.
|
|
|
 |
Department of Computer Science & Engineering University of Washington Box 352350 Seattle, WA 98195-2350 (206) 543-1695 voice, (206) 543-2969 FAX |