Proposal for Ph.D. General Examinations
Xinyu Hugo Liu
Submitted April 13, 2004
Introduction
How can a machine represent a person as a richly social and psychological entity? How can a machine learn deeply about a person by reading personal narrative texts? How can these social and psychological models be leveraged to engage and maintain an intimate relationship with a person that is inspiring, meaningful, and long-lasting? These questions are important if we are to build machines that can understand, communicate, and relate to people like another person can. Answering these questions requires giving a machine the ability to construct socio-psychological models of a person’s identity, culture, personality, intuition, memory, and aesthetics, and to exploit these models to maintain subtle channels of social communication, such as social signaling, grooming, and empathy. My goal in the general exam is to study the areas pertinent to representing and communicating with a person as a socio-psychological entity.
This exam includes areas that look at humans through the various eyes of social psychologists, cognitive AI practitioners, and a linguists. The main area covers deep AI models of cognition that have been proposed and built over the past 50 years. The technical supporting area covers techniques for machine narrative comprehension. The contextual supporting area surveys the philosophy, sociology, and psychology of social identity.
Main Area:
Deep Computer Models of Cognition
Examiner
Pattie Maes
Associate Professor
MIT Media Laboratory
Description
The main area of this exam covers work in cognitive AI that puts forth models of human cognition, covering various issues such as knowledge representation, reasoning, behavior, affect, and learning. This literature represents the various points of view of researchers who approach AI through the lenses of multiple representations, logic, behavior-based agents, statistical learning, and philosophy.
Signature______Date______
Written Requirement
The written requirement will consist of a publishable quality paper to be graded by Professor Maes.
Reading List
Multiple representations
Marvin Minsky: 1986, The Society of Mind, New York: Simon & Schuster. [book]
Marvin Minsky: forthcoming, The Emotion Machine. New York: Pantheon. [link]
Marvin Minsky: 1974, A framework for representing knowledge (AI Laboratory Memo 306). Artificial Intelligence Laboratory, Massachusetts Institute of Technology. [link]
Randall Davis, Howard Shrobe, Peter Szolovits: 1993, “What is a Knowledge Representation?” AI Magazine, 14(1):17-33. [link]
Tim Berners-Lee et al: 2001, “The Semantic Web” Scientific American, May, 2001. [link]
Logic, reasoning, and planning
John McCarthy: 1958, Programs with Common Sense. Proceedings of the Teddington Conference on the Mechanization of Thought Processes. [link]
John McCarthy: 1990, Formalizing common sense. Norwood, NJ: Ablex [link]
A. Newell & H. A. Simon: 1963, GPS, a program that simulates human thought. In E. A. Feigenbaum and J. Feldman (eds.), Computers and Thought, pages 279-293. New York: McGraw-Hill. [?]
J. F. Lehman et al.: 1996, A gentle introduction to Soar, an architecture for human cognition. In S. Sternberg & D. Scarborough (eds.) Invitation to Cognitive Science (Volume 4). [link]
A. Newell: 1990, Unified Theories of Cognition, Cambridge, MA: Harvard University Press. [book]
M. P. Georgeff et al.: 1998, The Belief-Desire-Intention Model of Agency. In N. Jenning, J. Muller, and M. Wooldridge (eds.), Intelligent Agents V. Springer. [link]
Stuart Russell & Peter Norvig: 2002, AI: A Modern Approach, Prentice Hall. [book]
Martha Pollack: 1992, “The uses of plans,” AI Journal:57 [link]
Behavior-based models
Rod Brooks: 1991, “Intelligence Without Representation”, Artificial Intelligence Journal (47), 1991, pp. 139–159. [link]
Rod Brooks: 1991, “Intelligence without Reason.” Proceedings International Joint Conference on Artificial Intelligence '91, 569-595 (1991) [link]
Rod Brooks, Cynthia Breazeal, Matthew Marjanovic, Brian Scassellati, Matthew Williamson: 1999, "The Cog Project: Building a Humanoid Robot" in Computation for Metaphors, Analogy, and Agents. C. Nehaniv (ed.), Lecture Notes in Artificial Intelligence 1562. New York, Springer, 52–87, 1999. [link]
Rod Brooks: 2002, Flesh and Machines: How Robots Will Change Us. Pantheon. [book]
Pattie Maes: 1994, Modeling Adaptive Autonomous Agents, Artificial Life Journal, C. Langton, ed., Vol. 1, No. 1 & 2, MIT Press, 1994. [link]
L. Steels: 1994, The artificial life roots of artificial intelligence. Artificial Life Journal, Vol 1,1. MIT Press, Cambridge. [link]
Models of affect
Aaron Sloman: 1981, Why robots will have emotions. Proceedings of the Seventh International Joint Conference on Artificial Intelligence. [link]
A. Ortony, G.L. Clore, A. Collins: 1988, The cognitive structure of emotions, New York: Cambridge University Press. [book]
Rosalind Picard: 1997, Affective Computing, MIT Press. [book]
Margaret Boden: 1996, Artificial Genius, Discover Magazine, 17:10. [link]
Marvin Minsky: 1981, Jokes and the logic of the unconscious. In Vaina and Hintikka (eds.), Cognitive Constraints on Communication. Reidel. [link]
Learning models
L.P. Kaelbling, L.M. Littman and A.W. Moore: 1996, "Reinforcement learning: a survey," Journal of Artificial Intelligence Research, vol. 4, pp. 237—285. [link]
Andrew P. Duchon, William H. Warren, and Leslie Pack Kaelbling: 1998, “Ecological Robotics,” Adaptive Behavior, Volume 6, Number 3/4. [link]
S. Thrun and T. M. Mitchell: 1995, “Lifelong robot learning”, Robotics and Autonomous Systems, vol. 15, pp. 24-46. [link]
Tom M. Mitchell and Sebastian B. Thrun: 1995, Learning Analytically and Inductively. In Steier and Mitchell, editors, Mind Matters: A Tribute to Allen Newell. Erlbaum. [link]
Case-based reasoning
C. K. Riesbeck and R. C. Schank: 1989, Inside Case-Based Reasoning. Lawrence Erlbaum Associates, Hillsdale. [book]
Kristian Hammond, 1990: Explaining and Repairing Plans That Fail. Artificial Intelligence 45, pp. 173-228. [?]
Leake, David B.: 1996. Case-Based Reasoning: Experiences, Lessons, & Future Directions. Menlo Park, California: AAAI Press. [?]
Philosophy & AI
Aaron Sloman: 1996, What sort of architecture is required for a human-like agent? Cognitive Modeling Workshop, AAAI96, Portland Oregon, August. [link]
Aaron Sloman: 1995, A Philosophical Encounter, IJCAI. [link]
Daniel Dennett: 1992, Consciousness Explained. [book]
Margaret Boden (ed.): 1990, The Philosophy of Artificial Intelligence, Oxford University Press, New York. [book]
Contextual Area: Building Blocks of Identity
Examiner
Judith Donath
Assistant Professor
MIT Media Laboratory
Description
My contextual supporting area looks at the issue of identity through the broader lens of Sociology, Psychology, and Philosophy. The readings in this area represent relevant contemporary social theories of identity, and nominates social objects, fashion, language, and media narratives as some of the primary building blocks for the social composition of identity. I also examine social signaling theory as a framework for understanding how identity is revealed or “given off” in social communication with other people (and machines). Through this literature I hope to attain a broader understanding of identity – how it is perceived by ego and alter, and what it is composed off – that will inform me in the design of rich socio-psychological computer models of a person. Only after we have addressed the issues of social identity can we have sociable computers that can inspire and relate to us at a more intuitive and intimate level.
Signature______Date______
Written Requirement
The written requirement will consist of a publishable quality paper to be graded by Professor Donath.
Reading List
The sociological concept of “identity”
Kurt Wolff (ed., trans.): 1950, The Sociology of Georg Simmel, Glencoe: Free Press. [book]
D. N. Levine (ed.): 1971, On Individuality and Social Forms: Selected Writings, University of Chicago Press, Chicago. [book]
Erving Goffman: 1959, The Presentation of Self in Everyday Life. Doubleday: Garden City, New York. [book]
The social meanings of objects
Mihaly Csikszentmihalyi, Eugene Rochberg-Halton: 1981, The Meaning of Things: Domestic Symbols and the Self, Cambridge University Press, UK. [book]
David Halle: 1993, Inside Culture: Art and Class in the American Home, University of Chicago Press, Chicago. [book]
Fashion in identity
Sarah Thornton: 1996, Club Cultures: Music, Media and Subcultural Capital, Wesleyan University Press. [book]
Grant McCracken: 1991, Culture and Consumption: New Approaches to the Symbolic Character of Consumer Goods and Activities, Indiana University Press, Indiana. [book]
Fred Davis: 1994, Fashion, Culture, and Identity, University of Chicago Press, Chicago. [book]
Sociolinguistics
George Lakoff, Mark Johnson: 1980, Metaphors We Live by. University of Chicago Press. [book]
Peter Trudgill: 2001, Sociolinguistics: An Introduction to Language and Society, Penguin USA. [book]
Muriel Saville-Troike: 1989, The Ethnography of Communication. New York: Basil Blackwell. [book]
Roland Barthes: 1970, Mythologies, Paris: Seuil. [book]
Media and narratives in identity construction
Kevin Murray: 1990, Life as fiction, Ph.D. Dissertation, Department of Psychology, University of Melbourne. [link]
Kevin Murray: 1988, The construction of identity in the narratives of romance and comedy. In J.Shotter & K.Gergen (eds.) Texts of Identity London: Sage. [link]
Daniel Chandler: 1998: Personal Home Pages and the Construction of Identities on the Web. Available at: [link]
Debra Grodin, Thomas Lindlof (eds.): 1996, Constructing the Self in a Mediated World, Thousand Oaks, CA: Sage. [book]
Signaling theory (how is identity given off?)
Tim Guilford, and Marian Stamp Dawkins: 1993, Receiver psychology and the design of animal signals. Trends in the Neurosciences 16:430-436. [?]
A. Grafen: 1990a, Biological Signals as Handicaps, Journal of Theoretical Biology, 144:517-546. [hardcopy]
T. Veblen: 1899, The Theory of the Leisure Class, New York: Dover Publications. [book]
Technical Area:
Techniques for Narrative Comprehension
Examiner
Erik T. Mueller
Research Staff Member
IBM Thomas J. Watson Research Center
Description
This technical area covers work on machine narrative comprehension, also known as story understanding, embedded within the broader field of computational linguistics. As the literature on machine narrative comprehension is quite extensive, I give special treatment to models and techniques of comprehension that are semantically informed, that is to say, comprehension beyond strict parsing, and involving projection, creative inference, and situated understanding. I also include a section on techniques for creative narrative generation, which is a perfect complement to comprehension in the context of person-to-person communication.
Signature______Date______
Written Requirement
The written requirement will consist of an implementation project and publishable quality paper to be graded by Dr. Mueller.
Reading List
Scripts, plans, goals, TAUs, plot units, and situation models for narrative comprehension
M.G. Dyer: 1983, In-depth understanding. Cambridge, Mass.: MIT Press. [book]
R.C. Schank & R.P. Abelson: 1977, Scripts, plans, goals, and understanding. Hillsdale, NJ: Lawrence Erlbaum. [book]
W.G. Lehnert: 1982, Plot units: A narrative summarization strategy. In W. G. Lehnert & M. H. Ringle (Eds.). Strategies for natural language processing. Hillsdale, NJ: Lawrence Erlbaum Associates. [?]
Rolf A. Zwaan & Gabriel A. Radvansky: 1998, Situation models in
language comprehension and memory. Psychological Bulletin, 123(2), 162-185. [?]
Logic-based techniques for narrative comprehension
Jerry R. Hobbs, Mark E. Stickel, Douglas Appelt, & Paul Martin: 1993, “Interpretation as abduction.” In Fernando C. N. Pereira & Barbara J. Grosz (Eds.), Natural language processing
(pp. 69-142). Cambridge, MA: MIT [link]
Murray Shanahan: 1997, Solving the frame problem. Cambridge, MA:
MIT Press. [book]
Probabilistic and connectionist methods for narrative comprehension
Robert P. Goldman: 1990, A probabilistic approach to language
understanding (Technical Report CS-90-34). Providence, RI: Computer Science Department, Brown University. [?]
Stefan L. Frank, Mathieu Koppen, Leo G. M. Noordman, Wietske Vonk: 2003, Modeling knowledge-based inferences in story
comprehension. Cognitive Science, 27, 875-910. [?]
Srinivas S. Narayanan: 1997, Knowledge-based action representations
for metaphor and aspect (KARMA) (Unpublished doctoral
dissertation). University of California, Berkeley. [link]
Serendipity and explanation in creative narrative comprehension
E.A. Domeshek, 1994: “Abby: Exploring an Indexing Vocabulary for Social Advice.” In Roger Schank, Alex Kass (eds), Inside Case-Based Explanation. Hillsdale, NJ: Lawrence Erlbaum. [book]
Erik Mueller: 1990, Daydreaming in humans and computers: a computer model of stream of thought. Norwood, NJ: Ablex. [book]
David Gelernter: 1994, The Muse in the Machine: Computerizing the Poetry of Human Thought. Free Press. [book]
Ashwin Ram: 1994, “AQUA: Questions that drive the explanation process.” In Roger C. Schank, Alex Kass, & Christopher K. Riesbeck (Eds.), Inside case-based explanation (pp. 207-261). Hillsdale, NJ: Erlbaum. [link]
Creative reading
Kenneth Moorman & Ashwin Ram: 1994, A functional theory of creative reading. The Psycgrad Journal. Technical Report GIT-CC-94/01, College of Computing, Georgia Institute of Technology, Atlanta, GA, 1994. [link]
Kenneth Moorman & Ashwin Ram: 1994, Integrating creativity and
reading: A functional approach. In Sixteenth Annual Conference of the Cognitive Science Society. [link]
Creative narrative generation
C.B. Callaway: 2000, Narrative prose generation, Ph.D. Thesis, North Carolina State University, Raleigh, NC. [link]
Scott Turner: 1994, The Creative Process: A Computer Model of Storytelling and Creativity. NJ: Lawrence Erlbaum. [book]