Cross-situational learning: a mathematical approach

Authors:
Kenny Smith;Andrew D. M. Smith;Richard A. Blythe;Paul Vogt
Affiliations:
Language Evolution and Computation Research Unit, University of Edinburgh;Language Evolution and Computation Research Unit, University of Edinburgh;School of Physics, University of Edinburgh;Language Evolution and Computation Research Unit, University of Edinburgh
Venue:
EELC'06 Proceedings of the Third international conference on Emergence and Evolution of Linguistic Communication: symbol Grounding and Beyond
Year:
2006

Citing 4
Cited 7

Generating functionology

Generating functionology
Establishing Communication Systems without Explicit Meaning Transmission

ECAL '01 Proceedings of the 6th European Conference on Advances in Artificial Life
Intelligent meaning creation in a clumpy world helps communication

Artificial Life
Weaving a Lexicon

Weaving a Lexicon

Learning Meaning Before Syntax

ICGI '08 Proceedings of the 9th international colloquium on Grammatical Inference: Algorithms and Applications
Joint attention and language evolution

Connection Science - Social Learning in Embodied Agents
Flexible word meaning in embodied agents

Connection Science - Social Learning in Embodied Agents
A method for noise-robust context-aware pattern discovery and recognition from categorical sequences

Pattern Recognition
A hybrid model for learning word-meaning mappings

EELC'06 Proceedings of the Third international conference on Emergence and Evolution of Linguistic Communication: symbol Grounding and Beyond
Computational modeling of phonetic and lexical learning in early language acquisition: Existing models and future directions

Speech Communication
Individual semiosis in multi-agent systems

Transactions on Computational Collective Intelligence VII

Quantified Score

Hi-index	0.00

Visualization

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.