Paul Smolensky

Paul Smolensky

Krieger-Eisenhower Professor

PhD, Indiana University

Krieger 241B
Away Fall 2020
410-516-5331
smolensky@jhu.edu
Curriculum Vitae
Personal Website
Google Scholar Profile

My research (see Research tab) focuses on integrating symbolic and neural network computation for modeling reasoning and, especially, grammar in the human mind/brain. The work is formal and computational, with emerging applications to neuroscience and applied natural language processing. My research has primarily addressed issues of representation and processing rather than learning. Principal contributions  (see Publications tab) are to linguistic theory, the theory of vectorial neural network computation, and the philosophical foundations of cognitive science.

During Fall semesters I am on leave from Johns Hopkins, working at Microsoft Research in Redmond, Washington (for a non-technical synopsis of some of my recent work there, see this link: Mind/Brain Networks). Prior to joining the faculty of the Cognitive Science Department at Johns Hopkins, I was a professor in the Computer Science Department and Institute of Cognitive Science at the University of Colorado Boulder. I had been a postdoc at the Center for Cognitive Science at the University of California at San Diego, where I was a founding member of the Parallel Distributed Processing Research Group and worked with Dave Rumelhart, James McClelland and Geoff Hinton. (I also contributed to the User-Centered System Design group led by Don Norman.) My degrees are an A.B. in Physics from Harvard and, from Indiana University, Bloomington, a M.S. in Physics and a Ph.D. in Mathematical Physics.

Goal

Unification of the sciences of mind & brain through integration of

  • compositional, structured, symbolic computation
    • at the core of many successful classical theories of the mind
      • in particular, the theory of language
    • a branch of discrete mathematics
  • dynamic, distributed, vectorial connectionist computation
    • at the core of the theory of neural networks, crucial for
      • computational models of the brain
      • emergentist models of the mind
      • contemporary machine learning and Artificial Intelligence
    • a branch of continuous mathematics

Current

The theory, and application to language, of Gradient Symbolic Computation, a new cognitive architecture in which a single computational system can simultaneously be described formally at two levels:

  • a higher ‘abstract mental’ level, where
    • data
      • consist of symbols that have partial degrees of presence — gradient activity levels
      • which blend together to form Gradient Symbol Structures (such as gradient trees)
    • processing
      • is algebraic operations on vectors and tensors
  • a lower ‘abstract neural’ level, where
    • data
      • consist of distributed activation vectors over many model neurons
      • which superimpose to implement Gradient Symbol Structures…
    • processing
      • is probabilistic spreading of activation (governed by stochastic differential equations)
      • through networks with numerically weighted interconnections
  • AS.050.326/626 Foundations of Cognitive Science.
  • AS.050.372/672 Foundations of Neural Network Theory
  • AS.050.829. Research Seminar on Formal Theory in Cognitive Science

Below is a list of my primary and secondary PhD student advisees since 1995. To view a complete list of my department’s PhD alumni, please visit our Alumni Placement webpage. 

edited 8/2016

Primary Advisor

Name

Current Position

Dissertation. Graduating Year.

Deepti Ramadoss 
(co-advisor:
  L. Burzio)

Assist. Director for Training, Assessment and Career Exploration, Univ. of Pittsburgh

The phonology and phonetics of tone perception. 2011.

Jennifer Culbertson
(co-advisor:
  G. Legendre)

Reader, Centre for Language Evolution, Univ. of Edinburgh

Learning biases, regularization, and the emergence of typological universals in syntax.  2010.

Rebecca Morley

Asst. Prof., Dept. of Linguistics, Ohio State Univ

Generalization, Lexical Statistics, and Typologically Rare Systems. 2008.

Sara Finley

Assoc. Prof., Dept of Psychology, Pacific Lutheran Univ.

Formal and Cognitive Restrictions on Vowel Harmony. 2008.

Gaja Jarosz

Assoc. Prof., Dept  of Linguistics, UMass at Amherst

Rich Lexicons and Restrictive Grammars – Maximum Likelihood Learning in Optimality Theory. 2006.

Adam Buchwald
(co-advisor:
  B. Rapp)

Assoc. Prof., Dept of Communicative 
Sciences & Disorders, NYU

Sound structure representation, repair and well-formedness: Grammar in spoken language production. 2005.

Lisa Davidson

Professor, Dept. of Linguistics, NYU

The atoms of phonological representation: Gestures, coordination and perceptual features in consonant cluster phonotactics. 2003.

John Hale

Professor, Dept. of Linguistics & Institute for Artificial Intelligence, Univ. of Georgia

Grammar, uncertainty, and sentence processing. 2003.

Bruce Tesar

Professor, Dept of Linguistics, Rutgers

Computational Optimality Theory. 1995.
Computer Science, Univ of Colorado

Secondary Advisor

Name

 Current Position

Dissertation. Graduating Year.

Tamara Nicol Medina
(primary advisor:
  B. Landau)

Asst. Prof. – Teaching, Dept. of Psychology, Univ. of Delaware

Learning which verbs allow object omission: Verb semantic selectivity and the implicit object construction. 2007.

Matthew Goldrick
(primary advisor:
  B. Rapp)

Professor, Dept. of Linguistics, Northwestern

Patterns in sound, patterns in mind: Phonological regularities in speech production. 2002.

Colin Wilson
(primary advisor:
  L. Burzio)

Professor, Dept. of Cognitive Science,  JHU

Targeted Constraints: An Approach to Positional Neutralization in Optimality Theory. 2000.

Adamantios Gafos
(primary advisor:
  L. Burzio)

Professor, Dept. of Linguistics, Postdam Univ.

The Articulatory Basis of Locality in Phonology. 1996.

Vertical integration of neural and symbolic computation: Theory and application
January 5, 2018,  Salt Lake City; Plenary lecture, inaugural meeting of the Society for Computation in Linguistics and symposium on Perceptrons & Syntactic Structures at 60

Neural networks and linguistic cognition
January 5, 2018,  Salt Lake City; Discussion session, Society for Computation in Linguistics and symposium

 
Discussion session featuring an all-JHU-Cogsci cast (left-to-right): Paul Smolensky (faculty), Matt Goldrick (PhD 2002), Tom McCoy (PhD student), Tal Linzen (faculty), Pyeong Whan Cho (postdoc)

Grammatical theory with Gradient Symbol Structures
January 12, 2016, Budapest; Research Institute for Linguistics, Hungarian Academy of Sciences

Four facts about Tensor Product Representations
December 12, 2015, Montreal; NIPS workshop Cognitive Computation: Integrating Neural and Symbolic Approaches

Gradient Symbols in Grammar
October 26, 2015; Mind, Technology and Society Talk Series, Cognitive and Information Sciences Department, University of California − Merced

Towards Understandable Neural Networks for High Level AI Tasks (short course on Tensor Product Representations)
Fall, 2015; Microsoft Research Talks

Does the success of deep neural network language processing mean — finally — the end of theoretical linguistics?
July 31, 2015, Beijing; Invited talk, with Jennifer Culbertson. CoNLL (Conference on Computational Natural Language Learning; SIGNLL of ACL)

Symbolic roles in vectorial computation
July 14, 2014, Redmond WA; Microsoft Research Faculty Summit panel, Deep Learning for Text Processing