CPSC 522 - Artificial Intelligence 2
Readings
January-April 2019
Readings
Where possible, I
have tried to find sources that are freely available. Some of them are
only free using a university computer (e.g. using the VPN). Some of
these are just names that you can google for. (For these Google seems
to give a good coverage). Some are more specific (when Google doesn't
seem to find good resources).
Some suggested topics for your esisting research assignment.
Your February assignment will need to cover a very specific research topic. Your
page will need to refer to at least two research papers (by disjoint
sets of authors)
and explain how one of the papers is an advance on the other. This
should be a different pair that one presented in class. Here is a
random selection of papers:
- Vibhav Gogate and Rina Dechter, SampleSearch: A Scheme that Searches for Consistent Samples, In 11th International Conference on Artificial Intelligence and Statistics (AISTATS), 2007.
- Daniel Lowd. Closed-Form Learning of Markov Networks from Dependency Networks. Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence (UAI-12), 2012. Catalina Island, CA.
- I. Shpitser, K. Mohan, and J. Pearl, "Missing data as a causal and probabilistic problem"
UCLA Cognitive Systems Laboratory, Technical Report (R-454), July 2015.
In Marina Meila and Tom Heskes (Eds.), Proceedings of the 31st
Conference on Uncertainty in Artificial Intelligence:
802--811, 2015. (or another paper from http://bayes.cs.ucla.edu/csl_papers.html)
- Sammut, C. A. (1988). Logic Programs as a Basis for Machine
Learning. and/or Sammut, C. A. (1993). The Origins of Inductive Logic
Programming. from Sammut's
pages on ILP
- Robot Scientist, e.g., https://dx.doi.org/10.1109%2FMC.2009.270
or http://science.sciencemag.org/content/324/5923/85
or http://rsif.royalsocietypublishing.org/content/12/104/20141289
- Restricted Boltzmann machines
- Rao Blackwellized particle filter
-
Barry Smith, Ontology, in L. Floridi (ed.), Blackwell Guide to
the Philosophy of Computing and Information, 2003 and/or John Sowa,
Future Directions for Semantic Systems, Intelligence-based Software
Engineering, 2011. Or another paper on ontologies, such as at http://ontology.buffalo.edu/smith/
or http://www.jfsowa.com/pubs/index.htm.
or
-
Koren, Y., Bell, R. and Volinsky, C., Matrix Factorization
Techniques for Recommender Systems, IEEE Computer 2009.
-
Markov Logic Networks
Matthew Richardson and Pedro Domingos
- Problog, theory, implementation or applications
- Blog and open-universe models (search google for "Blog and open-universe models")
- Record Linkage and identity uncertainty
-
Blei, Ng, and Jordan, "Latent Dirichlet Allocation", JAIR 3 (2003)
-
Darius Braziunas and Craig Boutilier, Elicitation of Factored Utilities,
AI Magazine 29(4):79--92, Winter (2008).
- Interactive preference eliciition
an
application in computational sustainability and a tool
- Matheson, J.E. (1990). Using influence diagrams to value information and control. In R.M. Oliver and J.Q. Smith (Eds.), Influence Diagrams, Belief Nets and Decision Analysis, chapter 1, pp. 25-48. Wiley.
-
Action Selection for MDPs: Anytime AO* vs. UCT,
Blai Bonet and Hector Geffner.
Proc. 26th AAAI Conf. on Artificial Intelligence (AAAI). Toronto, Canada. 2012. Pages 1749-1755.
-
Cognitive Robotics Levesque, H. and Lakemeyer, G., Handbook of Knowledge Representation, Elsevier, 2008.
-
Reinforcement Learning - RALP [Ron Parr 2010] or Pazis & Parr 2011
- Mnih, V., Kavukcuoglu, K., Silver, D., et al. (2015). Human-level
control through deep reinforcement learning. Nature, 518: 529-533. or
Silver, D., et al (2016). Mastering the game of go with deep neural
networks and tree search. Nature, 529(7587): 484-489. See also Samuel,
A.L. (1959). Some studies in machine learning using the game of checkers. IBM Journal on Research and Development, 3(3): 210–229.
Books
Much of the basics is covered in
- D. Poole and A. Mackworth Artificial Intelligence: Foundations of
Computational Agents (Cambridge University Press, 2nd edition, 2017)
- S. Russell and P. Norvig, Artificial Intelligence : A Modern
Approach, 3rd edn (Prentice-Hall, 2010)
- D. Koller and N. Friedman. Probabilistic Graphical Models:
Principles and Techniques. (MIT Press 2009)
- A. Darwiche, Modeling and Reasoning with Bayesian Networks
(Cambridge University Press, 2010)
- De Raedt, L.; Frasconi, P.; Kersting, K.; Muggleton,
S.H. (Eds.), Probabilistic Inductive Logic Programming
Springer, 2008
- S. Thrun, W. Burgard and D. Fox, Probabilistic Robotics, (MIT Press
2006)
- Martijn van Otterlo, The Logic of Adaptive Behavior -
Knowledge Representation and Algorithms for Adaptive Sequential
Decision Making under Uncertainty in First-Order and Relational
Domains, (IOS Press, 2009).
- Luc De Raedt.
Logical and Relational Learning.
Springer.2008.
Journals and Conferences
The major journals and conferences related to this course are:
Ontologies
Philosophy and Practice of Science
There are lot of
books about science, pseudoscience and non-science --- this is very
relevant to the course as science is one of the best-developed mechanisms for
discovering what is true in the world. See, e.g., The Scientific
Method Made Easy.
Probabilistic Relational Models
Decision-theoretic Planning and Reinforcement Learning
- Boutilier, Dean
and Hanks ``Decision Theoretic Planning: Structural Assumptions and
Computational Leverage'', JAIR, Vol 11, 1--94, 1999
- Kaelbling, L.P., Littman, M.L., and Moore, A.W. (1996) "Reinforcement
Learning: A Survey", JAIR,
Volume 4, pages 237-285.
- Csaba Szepesvari, Algorithms
for Reinforcement Learning, Morgan & Claypool, 2010.
Causality
Last updated: 2013-01-01, David Poole