Book Chapter

Cross-situational learning: A mathematical approach

Citation

Smith K, Smith ADM, Blythe R & Vogt P (2006) Cross-situational learning: A mathematical approach. In: Vogt P, Sugita Y, Tuci E & Nehaniv (eds.) Symbol Grounding and Beyond: Third International Workshop on the Emergence and Evolution of Linguistic Communication, EELC 2006, Rome, Italy, September 30 – October 1, 2006. Proceedings. Lecture Notes in Computer Science, 4211. Heidelberg: Springer, pp. 31-44. http://link.springer.com/chapter/10.1007/11880172_3#; https://doi.org/10.1007/11880172_3

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 are 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. |

StatusPublished
Title of seriesLecture Notes in Computer Science
Number in series4211
Publication date31/12/2006
PublisherSpringer
Publisher URLhttp://link.springer.com/chapter/10.1007/11880172_3#
Place of publicationHeidelberg
ISSN of series0302-9743
ISBN978-3-540-45769-5