Paul Smolensky (born May 5, 1955) is Krieger-Eisenhower Professor of

Cognitive Science Cognitive science is the interdisciplinary, scientific study of the mind and its processes. It examines the nature, the tasks, and the functions of cognition (in a broad sense). Mental faculties of concern to cognitive scientists include percep ...

at the

Johns Hopkins University The Johns Hopkins University (often abbreviated as Johns Hopkins, Hopkins, or JHU) is a private university, private research university in Baltimore, Maryland, United States. Founded in 1876 based on the European research institution model, J ...

and a Senior Principal Researcher at

Microsoft Research Microsoft Research (MSR) is the research subsidiary of Microsoft. It was created in 1991 by Richard Rashid, Bill Gates and Nathan Myhrvold with the intent to advance state-of-the-art computing and solve difficult world problems through technologi ...

, Redmond Washington. Along with Alan Prince, in 1993 he developed

Optimality Theory Optimality theory (frequently abbreviated OT) is a linguistic model proposing that the observed forms of language arise from the optimal satisfaction of conflicting constraints. OT differs from other approaches to phonological analysis, which ty ...

, a grammar formalism providing a formal theory of cross-

linguistic typology Linguistic typology (or language typology) is a field of linguistics that studies and classifies languages according to their structural features to allow their comparison. Its aim is to describe and explain the structural diversity and the co ...

(or Universal Grammar) within

linguistics Linguistics is the scientific study of language. The areas of linguistic analysis are syntax (rules governing the structure of sentences), semantics (meaning), Morphology (linguistics), morphology (structure of words), phonetics (speech sounds ...

. Optimality Theory is popularly used for

phonology Phonology (formerly also phonemics or phonematics: "phonemics ''n.'' 'obsolescent''1. Any procedure for identifying the phonemes of a language from a corpus of data. 2. (formerly also phonematics) A former synonym for phonology, often pre ...

, the subfield to which it was originally applied, but has been extended to other areas of linguistics such as

syntax In linguistics, syntax ( ) is the study of how words and morphemes combine to form larger units such as phrases and sentences. Central concerns of syntax include word order, grammatical relations, hierarchical sentence structure (constituenc ...

and

semantics Semantics is the study of linguistic Meaning (philosophy), meaning. It examines what meaning is, how words get their meaning, and how the meaning of a complex expression depends on its parts. Part of this process involves the distinction betwee ...

. Smolensky is the recipient of the 2005

Rumelhart Prize The David E. Rumelhart Prize for Contributions to the Theoretical Foundations of Human Cognition was founded in 2001 in honor of the cognitive scientist David Rumelhart to introduce the equivalent of a Nobel Prize for cognitive science. It is aw ...

for his development of the ICS Architecture, a model of cognition that aims to unify

connectionism Connectionism is an approach to the study of human mental processes and cognition that utilizes mathematical models known as connectionist networks or artificial neural networks. Connectionism has had many "waves" since its beginnings. The first ...

and

symbolism Symbolism or symbolist may refer to: *Symbol, any object or sign that represents an idea Arts *Artistic symbol, an element of a literary, visual, or other work of art that represents an idea ** Color symbolism, the use of colors within various c ...

, where the symbolic representations and operations are manifested as abstractions on the underlying connectionist or

artificial neural networks In machine learning, a neural network (also artificial neural network or neural net, abbreviated ANN or NN) is a computational model inspired by the structure and functions of biological neural networks. A neural network consists of connected ...

. This architecture rests on

Tensor Product In mathematics, the tensor product V \otimes W of two vector spaces V and W (over the same field) is a vector space to which is associated a bilinear map V\times W \rightarrow V\otimes W that maps a pair (v,w),\ v\in V, w\in W to an element of ...

Representations, compositional embeddings of symbolic structures in vector spaces. It encompasses the Harmonic Grammar framework, a connectionist-based numerical grammar formalism he developed with

Géraldine Legendre Géraldine Legendre (born 1953) is a French-American cognitive scientist and linguist known for her work on French grammar, on mathematical models for the development of syntax in natural languages including harmonic grammar and Optimality Theo ...

and Yoshiro Miyata, which was the predecessor of

. The ICS Architecture builds on Harmony Theory, a formalism for

artificial neural network In machine learning, a neural network (also artificial neural network or neural net, abbreviated ANN or NN) is a computational model inspired by the structure and functions of biological neural networks. A neural network consists of connected ...

s that introduced the

restricted Boltzmann machine A restricted Boltzmann machine (RBM) (also called a restricted Sherrington–Kirkpatrick model with external field or restricted stochastic Ising–Lenz–Little model) is a generative stochastic artificial neural network that can learn a prob ...

architecture. This work, up through the early 2000s, is presented in the two-volume book written with Géraldine Legendre, ''The Harmonic Mind''. Subsequent work introduced ''Gradient Symbolic Computation'', in which blends of partially-activated symbols occupy blends of positions in discrete structures such as trees or graphs. This has been successfully applied to numerous problems in theoretical linguistics where traditional discrete linguistic structures have proved inadequate, as well as incremental sentence processing in psycholinguistics. In work with colleagues at Microsoft Research and Johns Hopkins, Gradient Symbolic Computation has been embedded in neural networks using deep learning to address a range of problems in reasoning and natural language processing. Among his other important contributions is the notion of local conjunction of linguistic constraints, in which two constraints combine into a single stronger constraint that is violated only when both of its conjuncts are violated within the same specified local domain. Local conjunction has been applied to the analysis of various "super-additive" effects in Optimality Theory. With Bruce Tesar (

Rutgers University Rutgers University ( ), officially Rutgers, The State University of New Jersey, is a Public university, public land-grant research university consisting of three campuses in New Jersey. Chartered in 1766, Rutgers was originally called Queen's C ...

), Smolensky has also contributed significantly to the study of the learnability of Optimality Theoretic grammars (in the sense of

computational learning theory In computer science, computational learning theory (or just learning theory) is a subfield of artificial intelligence devoted to studying the design and analysis of machine learning algorithms. Overview Theoretical results in machine learning m ...

). Smolensky was a founding member of the

Parallel Distributed Processing Connectionism is an approach to the study of human mental processes and cognition that utilizes mathematical models known as connectionist networks or artificial neural networks. Connectionism has had many "waves" since its beginnings. The first ...

research group at the

University of California, San Diego The University of California, San Diego (UC San Diego in communications material, formerly and colloquially UCSD) is a public university, public Land-grant university, land-grant research university in San Diego, California, United States. Es ...

, and is currently a member of the Center for Language and Speech Processing at

and of the Deep Learning Group at

, Redmond Washington.

References

External links

Paul Smolensky Homepage at Johns Hopkins

Paul Smolensky Homepage at Microsoft Research

David E. Rumelhart Prize
{{DEFAULTSORT:Smolensky, Paul 1955 births Harvard University alumni Indiana University alumni Living people Phonologists from the United States Johns Hopkins University faculty Rumelhart Prize laureates Fellows of the Cognitive Science Society