Cross-situational learning: A mathematical approach

Kenneth Smith, Andrew D. M. Smith, Richard A. Blythe, Paul Vogt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a mathematical model of cross-situational learning, in which we quantify the learnability of words and vocabularies. We find that high levels of uncertainty axe not an impediment to learning single words or whole vocabulary systems, as long as the level of uncertainty is somewhat lower than the total number of meanings in the system. We further note that even large vocabularies are learnable through cross-situational learning.

Original languageEnglish
Title of host publicationSYMBOL GROUNDING AND BEYOND, PROCEEDINGS
EditorsP Vogt, Y Sugita, E Tuci, C Nehaniv
Place of PublicationBERLIN
PublisherSpringer
Pages31-44
Number of pages14
ISBN (Print)3-540-45769-0
Publication statusPublished - 2006
Event3rd Annual International Wokshop on Emergence and Evolution of Linguistic Communication - Rome
Duration: 30 Sept 20061 Oct 2006

Conference

Conference3rd Annual International Wokshop on Emergence and Evolution of Linguistic Communication
CityRome
Period30/09/061/10/06

Fingerprint

Dive into the research topics of 'Cross-situational learning: A mathematical approach'. Together they form a unique fingerprint.

Cite this