• Documents
  • Authors
  • Tables
  • Other Seers ▼
    RefSeer AckSeer CollabSeer SeerSeer
  • Log in
  • Sign up
  • MetaCart

CiteSeerX logo

Advanced Search Include Citations
Advanced Search Include Citations | Disambiguate

Finding structure in time (1990)

Cached

  • Download as a PDF

Download Links

  • [www.cs.swarthmore.edu]
  • [web.cs.swarthmore.edu]
  • [web.cs.swarthmore.edu]
  • [www.cs.swarthmore.edu]
  • [www.cnbc.cmu.edu]
  • [www.cs.utsa.edu]
  • [www-cse.ucsd.edu]
  • [crl.ucsd.edu]
  • [ftp.crl.ucsd.edu]

  • Other Repositories/Bibliography

  • DBLP
  • Save to List
  • Add to Collection
  • Correct Errors
  • Monitor Changes
by Jeffrey L. Elman
Venue:COGNITIVE SCIENCE
Citations:1314 - 17 self
  • Summary
  • Active Bibliography
  • Co-citation
  • Clustered Documents
  • Version History

Versions

  • Version 0
  • Version 1
  • Version 2

Version History

Metadata Version 2

User correction supplied by jfernandez

DatumValueSource
TITLE Finding structure in time INFERENCE
AUTHOR NAME Jeffrey L. Elman user correction
AUTHOR AFFIL University of California, San Diego user correction
ABSTRACT Time underlies many interesting human behaviors. Thus, the question of how to represent time in connectionist models is very important. One approach is to represent time implicitly by its effects on processing rather than explicitly (as in a spatial representation). The current report develops a proposal along these lines first described by Jordan (1986) which involves the use of recurrent links in order to provide networks with a dynamic memory. In this approach, hidden unit patterns are fed back to themselves; the internal representations which develop thus reflect task demands in the context of prior internal states. A set of simulations is reported which range from relatively simple problems (temporal version of XOR) to discovering syntactic/semantic features for words. The networks are able to learn interesting internal representations which incorporate task demands with memory demands; indeed, in this approach the notion of memory is inextricably bound up with task processing. These representations reveal a rich structure, which allows them to be highly context-dependent while also expressing generalizations across classes of items. These representations suggest a method for representing lexical categories and the type/token distinction. SVM HeaderParse 0.2
YEAR 1990 INFERENCE
VENUE COGNITIVE SCIENCE user correction
VENUE TYPE JOURNAL INFERENCE
PAGES 179--211 INFERENCE
VOLUME 14 INFERENCE
NUMBER 2 user correction
CITATIONS 36 found ParsCit 1.0
The National Science Foundation
  • About CiteSeerX
  • Submit Documents
  • Privacy Policy
  • Help
  • Data
  • Source
  • Contact Us

Developed at and hosted by The College of Information Sciences and Technology

© 2007-2010 The Pennsylvania State University