Home | People | Smolensky

		Paul Smolensky
			Courses
			Research
			Students
			Education
			Positions
			Presentations
			Publications
				Books
				Papers
					Grammar
					Computation
					Foundations
					Integration
					Others
			Complete Vita
	smolensky@jhu.edu Phone: 410-516-5114 Office: Krieger 241B Office Hours: by appointment
			Principles of Dave's Philosophy. From celebration honoring the career of David Rumelhart. Carnegie-Mellon University, October, 1999.

Courses (at Johns Hopkins)

• 050.109        Minds, Brains & Computers
• 050.313/613 Introduction to Cognition for Mathematical Scientists
• 050.325/625 Phonology I
• 050.326/626 Foundations of Cognitive Science
• 050.327/627 Phonology II
• 050.329/629 Phonology III
• 050.372/672 Formal Methods in Cognitive Science: Neural Networks
• 050.382/682 Intermediate Formal Methods in Cognitive Science: Neural Networks
• 050.823        Research Seminar in Phonology
• 050.830        Topics in Cognitive Science

back to top

Research

Primary Area: Universal grammar -- Optimality Theory: phonology, syntax, acquisition, learnability, processing.
Secondary Areas: Integration of connectionist ('neural') and symbolic computation: computational, linguistic, and philosophical issues.

Precise theories of higher cognitive domains like language and reasoning rely crucially on complex symbolic rule systems like those of grammar and logic. According to traditional cognitive science and artificial intelligence, such symbolic systems are the very essence of higher intelligence. Yet intelligence resides in the brain, where computation appears to be numerical, not symbolic; parallel, not serial; quite distributed, not as highly localized as in symbolic systems. Furthermore, when observed carefully, much of human behavior is remarkably sensitive to the detailed statistical properties of experience; hard-edged rule systems seem ill-equipped to handle these subtleties. My research attempts to identify the proper roles within a unified theory of cognition for symbolic computation, numerical neural computation, and statistical computation.

More specifically, the basic questions driving this research include: What are the central general principles of computation in connectionist -- abstract neural -- networks? How can these principles be reconciled with those of symbolic computation? Addressing these questions over the past two decades, my work has led to a new computational architecture for cognition which integrates connectionist and symbolic computation. Can this framework further the theory of higher cognition, by connecting it with lower-level principles derived from neural computation?

The connectionist conception of intuitive knowledge as a collection of conflicting soft constraints, interacting via optimization of well-formedness or Harmony, led in joint research with Géraldine Legendre to the connectionist-based formalism of Harmonic Grammar.Incorporating the richly tructured representations and universal well-formedness constraints of symbolic linguistic theory, Alan Prince and I developed a grammar formalism called Optimality Theory which brings general connectionist computational principles of optimization into the heart of the symbolic theory of universal grammar. The optimization that emerges is no longer inherently numerical: constraint strengths are encoded in a hierarchy of constraints, ranked from strongest to weakest; each constraint is stronger than all weaker constraints combined.

According to Optimality Theory (OT), possible human languages share a common set of universal constraints on well-formedness. These constraints are highly general, and hence conflict; thus some must be violated in optimal, i.e., grammatical, structures. The different surface patterns of the world's languages emerge via different priority rankings of the fixed set of universal constraints: each ranking is a language-particular grammar, a means of resolving the inherent conflicts among the universal constraints.

My current research addresses multiple aspects of OT. These include superadditive constraint interaction ('local conjunction' of constraints), especially in phonology (vowel harmony; Obligatory Contour Principle; sonority and syllable structure), as well as numerical and connectionist implementation of OT constraint interaction.

back to top

Ph.D. Students (since 1995)

back to top

Education

• Ph.D. in mathematical physics, Indiana University, 1981.
• M.S. in physics, Indiana University, 1977.
• A.B. summa cum laude in physics, Harvard University, 1976.

back to top

Positions

• Full Professor, Department of Cognitive Science, Johns Hopkins University, 1994-present.
• Chair, Department of Cognitive Science, Johns Hopkins University, Jan. 1997 - June 1998 (Acting), July 1998 - June 2000.



• Adjunct Professor, Department of Linguistics, University of Maryland at College Park, 1994-present.
• Assistant Director, Center for Language and Speech Processing, Johns Hopkins University, 1995-present.
• Director, NSF IGERT Training Program in the Cognitive Science of Language, 1999-2004.
  
  
• Professor, Department of Computer Science, University of Colorado at Boulder,
  Full Professor, 1994-95 (on leave, 1994-95).
  Associate Professor, 1990-94.
  Assistant Professor, 1985-90.
  
  
• Assistant Research Cognitive Scientist (Assistant Professor - Research), Institute for Cognitive Science, University of California at San Diego, 1982-85.
• Visiting Scholar, Program in Cognitive Science, University of California at San Diego, 1981-82.



• Faculty, First International Summer Institute in Cognitive Science, SUNY Buffalo, 1994.
• Faculty, Linguistic Institute, University of California at Santa Cruz, 1991.
• Faculty, Connectionist Models Summer School; Carnegie-Mellon University, 1986, 1988; University of California, San Diego, 1990; University of Colorado, Boulder, 1993.



• National Science Foundation, John H. Edwards, and Indiana University Graduate Fellow, 1976-81.

back to top

Recent Presentations

• An Integrated Connectionist/Symbolic (ICS) Cognitive Architecture. Seoul National University. November, 2002. [4.4Mb ppt file]
• Jakobson's Grand Unified Theory of Linguistic Cognition. Seoul National University. November, 2002. [.5Mb ppt file]
• Constraint Conjunction andStrong Harmonic Completeness. Korean Phonological Society. November, 2002.[0.6Mb ppt file]
• The Harmonic Mind. Cognition Workshop. North American Summer School for Logic, Language, and Information. Stanford University. July, 2002. [2.4Mb ppt file]
• Markedness Optimization in Grammar and Cognition. Plenary Lecture, Annual Meeting of the Linguistic Society of America. San Francisco. January, 2002. [1Mb ppt file]
• Formal Typology: Explanation in Optimality Theory. Phonology Forum. Tokyo, Japan. August, 2001. [0.5Mb ppt file]
• The Harmonic Mind. International Cognitive Science Conference. Beijing, China. August, 2001.[2Mb ppt file]
• The Harmonic Mind. Presidential Address, Annual Meeting of the Society for Philosophy and Psychology. Cincinnati, OH. June, 2001. [4Mb ppt file]

back to top

Publications
For a complete list, see the Complete Vita

ROA = http://ruccs.rutgers.edu/roa.html, the Rutgers Optimality Archive

Books

1. Smolensky, P., & Legendre, G. To appear. The harmonic mind: From neural computation to optimality-theoretic grammar.
2. Prince, A. & Smolensky, P. To appear. Optimality Theory: Constraint interaction in generative grammar. Blackwell. Complete ms. distributed April 1993 as Technical Report CU-CS-696-93, Department of Computer Science, University of Colorado at Boulder, and Technical Report TR-2, Rutgers Center for Cognitive Science, Rutgers University, New Brunswick, NJ. (234 pages). ROA 537.
3. Tesar, B. & Smolensky, P. 2000. Learnability in Optimality Theory. MIT Press.
4. Smolensky, P., Mozer, M. C., & Rumelhart, D. E. (eds.). 1996. Mathematical perspectives on neural networks. Lawrence Erlbaum Publishers.
5. Macdonald, C. & Macdonald, G. (eds.). 1995. Connectionism: Debates on psychological explanation, Volume 2. Basil Blackwell. [Contributed 4 chapters, 183 of 412 pp.]
6. Mozer, M.C., Smolensky, P., Touretzky, D., Elman, J., & Weigend, A. (eds.). 1993. Proceedings of the Connectionist Models Summer School 1993.Lawrence Erlbaum Publishers.
7. Smolensky, P. 1992. Il Connessionismo: Tra simboli e neuroni. Italian translation of the entire treatment, including peer commentary: On the proper treatment of connectionism, Behavioral and Brain Sciences, 11, 1-74; with introduction by Marcello Frixione. Genova: Marietti/Cambridge University Press.

Grammar

8. Hale, John & Smolensky, Paul. To appear. Harmonic Grammars and harmonic parsers for formal languages. In [1]. Chapter 10.
9. Legendre, Géraldine, Smolensky, Paul, & Miyata, Yoshiro. To appear. Harmonic Grammar and its subsymbolic foundations. In [1]. Chapter 11.
10. Smolensky, Paul & Tesar, Bruce. To appear. Principles of Optimality Theory. In [1]. Chapter 12.
11. Smolensky, Paul. To appear. Optimality in phonology II: Markedness, feature domains, and Local Constraint Conjunction. In [1]. Chapter 14.
12. Smolensky, Paul & Stevenson, Suzanne. To appear. Optimality in sentence processing. In [1]. Chapter 19.
13. Legendre, Géraldine, Sorace, Antonella & Smolensky, Paul. To appear. The Optimality Theory -- Harmonic Grammar connection. In [1]. Chapter 20.
14. Smolensky, Paul, Davidson, Lisa, and Jusczyk, Peter W. In press. The initial and final states: Theoretical implications and experimental explorations of richness of the base. In René Kager, Joe Pater and Wim Zonneveld, eds. Fixing Priorities: Constraints in Phonological Acquisition. Cambridge, England: Cambridge University Press. Reprinted in [1], Chapter 17. Rutgers Optimality Archive 428.
15. Moreton, Elliott, and Smolensky, Paul. 2002. Typological consequences of Local Constraint Conjunction. Proceedings of the 21st West Coast Conference on Formal Linguistics.
16. Jusczyk, P., Smolensky, P., and Allocco, T. 2002. How English-learning infants respond to markedness and faithfulness constraints. Language Acquisition .
17. Smolensky, P. 2000. Grammar-based connectionist approaches to language. Cognitive Science 23: 589-613. Reprinted in M. Christiansen and N. Chater. 2000. Connectionist Psycholinguistics. Ablex.
18. Tesar, B. & Smolensky, P. 1998. Learning Optimality-Theoretic grammars. Lingua, 106: 161-196. Reprinted in Sorace, A., Heycock, C. and Shillcock, R. (eds.) Language Acquisition: Knowledge Representation and Processing. Amsterdam: Elsevier.
19. Legendre, G., Smolensky, P., & Wilson, C. 1998. When is less more? Faithfulness and minimal links in wh-chains. In Pilar Barbosa, Danny Fox, Paul Hagstrom, Martha McGinnis, and David Pesetsky, eds., Is the Best Good Enough? Optimality and Competition in Syntax. MIT Press. 249-289
20. Tesar, B. & Smolensky, P. 1998. Learnability in Optimality Theory. Linguistic Inquiry, 29: 229-268
21. Prince, A. & Smolensky, P. 1997. Optimality: From neural networks to universal grammar. Science 275: 1604-1610.
22. Smolensky, P. 1996. On the comprehension/production dilemma in child language. Linguistic Inquiry 27: 720-731. ROA-118.
23. Smolensky, P. 1996. The initial state and 'richness of the base' in Optimality Theory. Accepted for publication in Linguistic Inquiry in 1997.Technical Report JHU-CogSci-96-4, Cognitive Science Department, Johns Hopkins University. ROA-154.
24. Legendre, G., Wilson, C., Smolensky, P., Homer, K., & Raymond, W. 1995. Optimality in wh-chains. University of Massachusetts Occasional Papers in Linguistics 18: Papers in Optimality Theory, J. Beckman, S. Urbanczyk, & L. Walsh, eds. Amherst, MA: GLSA, University of Massachusetts. 607-636. ROA-85.
25. Tesar, B. & Smolensky, P. 1994. The learnability of Optimality Theory. Proceedings of the West Coast Conference on Formal Linguistics XIII. 122-137.
26. Legendre, G., Raymond, W., & Smolensky, P. 1993. An Optimality-Theoretic typology of case and grammatical voice systems. Proceedings of the Nineteenth Annual Meeting of the Berkeley Linguistics Society. Berkeley, CA. February. 464-478. ROA-3.
27. Legendre, G., Miyata, Y., & Smolensky, P. 1991. Unifying syntactic and semantic approaches to unaccusativity: A connectionist approach. In L. Sutton & C. Johnson (with Ruth Shields) (Eds.), Proceedings of the Seventeenth Annual Meeting of the Berkeley Linguistics Society. Berkeley, CA. February. 156-167.
28. Prince, A. & Smolensky, P. 1991. Notes on Connectionism and Harmony Theory in Linguistics. Technical Report CU-CS-533-91, Department of Computer Science, University of Colorado at Boulder. July. [Notes from the course, 'Connectionism and Harmony Theory in Linguistics,' LSA Linguistic Institute, University of California, Santa Cruz; July, 1991.]
29. Smolensky, P. 1991. Connectionism. In W. Bright (Ed.) The International Encyclopedia of Linguistics. Oxford University Press. 294-297.
30. Legendre, G., Miyata, Y., & Smolensky, P. 1990. Can connectionism contribute to syntax? Harmonic Grammar, with an application. Proceedings of the 26th Meeting of the Chicago Linguistic Society. Chicago, IL. April.
31. Legendre, G., Miyata, Y., & Smolensky, P. 1990. Harmonic Grammar -- A formal multi-level connectionist theory of linguistic well-formedness: An application. Proceedings of the Twelfth Annual Conference of the Cognitive Science Society, Cambridge, MA. July. 884-891.
32. Legendre, G., Miyata, Y., & Smolensky, P. 1990. Harmonic Grammar -- A formal multi-level connectionist theory of linguistic well-formedness: Theoretical foundations. Proceedings of the Twelfth Annual Conference of the Cognitive Science Society, Cambridge, MA. July. 388-395.

    back to top

    Computation

33. Smolensky, P. (1996). Computational, dynamical, and statistical perspectives on the processing and learning problems in neural network theory. In [4]. 1-15.
34. Smolensky, P. (1996). Computational perspectives on neural networks. In [4]. 17-40.
35. Smolensky, P. (1996). Dynamical perspectives on neural networks. In [4]. 245-270.
36. Smolensky, P. (1996). Statistical perspectives on neural networks. In [4]. 453-496.
37. Tesar, B. & Smolensky, P. (1994). Synchronous-firing variable binding is spatio-temporal tensor product representation. Proceedings of the 16th Annual Conference of the Cognitive Science Society. Atlanta, GA. August.
38. Smolensky, P. (1993). Harmonic Grammars for formal languages. In S. Hanson, J. D. Cowan, & C. L. Giles, (Eds.), Advances in Neural Information Processing Systems 5, San Mateo, CA: Morgan Kaufmann. [Collected papers of the IEEE Conference on Neural Information Processing Systems-Natural and Synthetic, Denver, Nov. 1992.] 847-854.
39. Miyata, Y, Smolensky, P., & Legendre, G. (1993). Distributed representation and parallel processing of recursive structures. Proceedings of the 15th Annual Conference of the Cognitive Science Society, Boulder, CO. June. 759-764.
40. Legendre, G., Miyata, Y., & Smolensky, P. (1991). Distributed recursive structure processing. In Touretzky, D. S., Lippman, R. (Eds.), Advances in Neural Information Processing Systems 3. San Mateo, CA: Morgan Kaufmann. [Collected papers of the IEEE Conference on Neural Information Processing Systems-Natural and Synthetic, Denver, Nov. 1990.] 591-597. Slightly expanded version in Mayoh, B. (Ed.), Scandinavian Conference on Artificial Intelligence-91, 47-53. Amsterdam: IOS Press.
41. Smolensky, P. (1990). Tensor product variable binding and the representation of symbolic structures in connectionist networks. Artificial Intelligence, 46, 159-216. [Reprinted in G. Hinton, (Ed.), (1990), Connectionist symbol processing, Elsevier/MIT Press.]
42. Brousse, O. & Smolensky, P. (1990). Connectionist generalization and incremental learning in combinatorial domains. In H. Haken (Ed.), Synergetics of Cognition. Springer-Verlag. 70-80.
43. Smolensky, P. (1990). Representation in connectionist networks. Intellectica: The Journal of the French Association for Cognitive Research, 9-10, 127-165.
44. Mozer, M. C., & Smolensky, P. (1989). Using relevance to reduce network size automatically. Connection Science, 1, 3-16.
45. Dolan, C. & Smolensky, P. (1989). Tensor Product Production System: A modular architecture and representation. Connection Science, 1, 53-68.
46. Brousse, O. & Smolensky, P. (1989). Virtual memories and massive generalization in connectionist combinatorial learning. Proceedings of the Eleventh Annual Meeting of the Cognitive Science Society. Ann Arbor, MI. August. 380-387.
47. Smolensky, P. (1988). Analysis of distributed representation of constituent structure in connectionist systems. Proceedings of Neural Information Processing Systems-87. Denver, CO. November. 730-739.
48. McMillan, C. & Smolensky, P. (1988). Analyzing a connectionist model as a system of soft rules. Proceedings of the Tenth Annual Meeting of the Cognitive Science Society. Montreal, Canada. August. 62-68.
49. Smolensky, P. (1987). On variable binding and the representation of symbolic structures in connectionist systems. Technical Report CU-CS-355-87, Department of Computer Science, University of Colorado at Boulder. February.
50. Smolensky, P. (1986). Information processing in dynamical systems: Foundations of harmony theory. In D. E. Rumelhart, J. L. McClelland, & the PDP Research Group, Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Volume 1: Foundations. Cambridge, MA: MIT Press/Bradford Books. 194-281.
51. Smolensky, P. (1986). Neural and conceptual interpretations of parallel distributed processing models. In J. L. McClelland, D. E. Rumelhart, & the PDP Research Group, Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Volume 2: Psychological and Biological Models. Cambridge, MA: MIT Press/Bradford Books. 390-431.
52. Rumelhart, D. E., Smolensky, P., McClelland, J. L., & Hinton, G. E. (1986). Schemata and sequential thought processes in parallel distributed processing. J. L. McClelland, D. E. Rumelhart, & the PDP Research Group, Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Volume 2: Psychological and Biological Models. Cambridge, MA: MIT Press/Bradford Books. 7-57. [Reprinted in A. Collins & E. Smith (Eds), 1988, Readings in Cognitive Science, San Mateo, CA: Morgan Kaufmann.]
53. Smolensky, P. (1984). The mathematical role of self-consistency in parallel computation. Proceedings of the Sixth Annual Conference of the Cognitive Science Society. Boulder, CO. June. 319-325.
54. Riley, M. S. & Smolensky, P. (1984). A parallel model of (sequential) problem solving. Proceedings of the Sixth Annual Conference of the Cognitive Science Society. Boulder, CO. June. 286-292.
55. Smolensky, P. (1983). Schema selection and stochastic inference in modular environments. Proceedings of the National Conference on Artificial Intelligence. Washington, DC. August. 378-382.

back to top

Foundations

56. Smolensky, P. (1995). Constituent structure and explanation in an integrated connectionist/symbolic cognitive architecture. In [5]. 221-290.
57. Smolensky, P. (1994). Computational theories of mind. In S. Guttenplan (Ed.), A Companion to the Philosophy of Mind. Blackwell Publishers. 176-185.
58. Smolensky, P. (1991). Connectionism, constituency, and the language of thought. In B. Loewer & G. Rey (Eds.), Meaning in Mind: Fodor and his Critics. Oxford: Basil Blackwell. 201-227. Reprinted in [5].
59. Smolensky, P. (1989). Connectionist modeling: Neural computation/mental connections. In L. Nadel (Ed.), P. Culicover, L. A. Cooper, R. M. Harnish (Assoc. Eds.), Neural connections, mental computation. Cambridge, MA: MIT Press/Bradford. 49-67. [Reprinted in J. Haugeland, (Ed.). (1997). Mind Design II: Philosophy, Psychology, Artificial Intelligence, MIT Press/Bradford Books.]
60. Smolensky, P. (1987). The constituent structure of connectionist mental states: A reply to Fodor and Pylyshyn. Southern Journal of Philosophy, 26 (Supplement), 137-63. [Reprinted in T. Horgan & J. Tienson (Eds.), (1991), Connectionism and the Philosophy of Mind, Dordrecht: Kluwer Academic. 281-308; Spanish translation in E. Rabossi (Ed.), Filosofía y Ciencia Cognitiva, Buenos Aires-Barcelona: Editorial Paidós.]

    back to top

    Integration

61. Smolensky, P., Legendre, G., & Miyata, Y. (1993). Integrating connectionist and symbolic computation for the theory of language. Current Science 64, 381-391. Reprinted in: V. Honavar & L. Uhr, Artificial Intelligence and Neural Networks: Steps Toward Principled Integration, 509-530. Academic Press.
62. Smolensky, P., Legendre, G., & Miyata, Y. (1992). Principles for an Integrated Connectionist/Symbolic Theory of Higher Cognition. Technical Report CU-CS-600-92, Department of Computer Science and 92-8, Institute of Cognitive Science. University of Colorado at Boulder. (75 pages). Expanded to [1].
63. McNaughton, B. L. & Smolensky, P. (1991). Connectionist and neural modeling: Converging in the hippocampus. In R. G. Lister & H. J. Weingartner (Eds.), Perspectives on Cognitive Neuroscience. Oxford University Press. 93-109.
64. Smolensky, P. (1990). In defense of PTC: Reply to continuing commentary. Behavioral and Brain Sciences. 13, 407-411.
65. Smolensky, P. (1988). Putting Together Connectionism-again. Behavioral and Brain Sciences, 11, 59-74.
66. Smolensky, P. (1988). On the proper treatment of connectionism. Behavioral and Brain Sciences, 11, 1-23. [Reprinted in D. Cole, J. Fetzer, & T. Rankin (Eds.), (1990), Philosophy, Mind, and Cognitive Inquiry, Dordrecht: Kluwer Academic; A. I. Goldman, (1994), Readings in Philosophy and Cognitive Science, Cambridge: MIT Press/Bradford Books; and [5]; Italian translation published as monograph [7]; Hungarian translation in A Cognitive Science Reader, Budapest: Osiris Publishing House. (1997)]
67. Smolensky, P. (1987). Connectionist AI, symbolic AI, and the brain. Artificial Intelligence Review, 1, 95-109. [French translation with added post scriptum in D. Andler, (Ed.). (1992). Introduction aux sciences cognitives, Editions Gallimard.]

back to top

Others

68. Smolensky, P., Fox, B., King, R., Lewis, C. (1988). Computer-aided reasoned discourse, or, How to argue with a computer. In R. Guindon (Ed.), Cognitive Science and Its Applications For Human-Computer Interaction. Hillsdale, NJ: Erlbaum. 109-62.
69. Smolensky, P., Bell, B., Fox, B., King, R., & Lewis, C. (1987). Constraint-based hypertext for argumentation. Proceedings of Hypertext-87. Chapel Hill, NC. November. 215-245.
70. Smolensky, P., Monty, M. L. & Conway, E. (1984). Formalizing task descriptions for command specification and documentation. Proceedings of the International Federation of Information Processing Conference on Human-Computer Interaction. London, England. September. 603-609.
71. Greenspan, S. & Smolensky, P. (1984). DESCRIBE: Environments for Specifying Commands and Retrieving Information By Elaboration. In User centered system design, Part II, Technical Report No. 8402. Institute for Cognitive Science, University of California at San Diego. March.
72. O'Malley, C., Smolensky, P, Bannon, L., Conway, E., Graham, J., Sokolov, J., & Monty, M. L. (1983). A proposal for user centered system documentation. Proceedings of the CHI 1983 Conference on Human Factors in Computing Systems. Boston, MA. December.
73. Freedman, B., Smolensky, P, & Weingarten, D. H. (1982). Monte Carlo evaluation of the continuum limit of (j^4)_4 and (j^4)_3 field theory. Physics Letters B, 113, 481-486.
74. Smolensky, P. (1981). Lattice Renormalization of j^4 Theory. Doctoral thesis in mathematical physics, Indiana University.
75. Bradbury, K., Danziger, S., Smolensky, E., & Smolensky, P. (1979). Public assistance, female headship and economic well-being. Journal of Marriage and the Family, 519-535. [Reprinted in G. McDonald & F. Nye (Eds.), (1979), Family policy, National Council on Family Relations.]
76. Cicchetti, C., Gillen, W., & Smolensky, P. (1977). The Marginal Cost and Pricing of Electricity: An Applied Approach. Ballinger.

back to top

Revised: March 2, 2003