Full-text

URL: http://big.cs.uiuc.edu/~swarup/papers/NP...v/sg-sab06-final.pdf

Cached: PDF-205K

SAVE AS an easy-to-recall long filename:

Filename format: author--year--title   PDF-205K

Filename format: author--year--title--journal|proceedings|...--pages   PDF-205K

Related links

Authoritative: http://dx.doi.org/10.1007/11840541_63   (Publisher's PDF... likely be available here.)

Web search: Google Web Search   ::   Google Scholar

Within this site: Cited by (1)    References (16)

Abstract

We study the role of the agent interaction topology in distributed language learning. In particular, we utilize the replicator-mutator framework of language evolution for the creation of an emergent agent interaction topology that leads to quick convergence. In our system, it is the links between agents that are treated as the units of selection and replication, rather than the languages themselves. We use the Noisy Preferential Attachment algorithm, which is a special case of the replicator-mutator process, for generating the topology. The advantage of the NPA algorithm is that, in the short-term, it produces a scale-free interaction network, which is helpful for rapid exploration of the space of languages present in the population. A change of parameter settings then ensures convergence because it guarantees the emergence of a single dominant node which is chosen as teacher almost always

@inproceedings{swarup06SAB,
  author={Samarth Swarup and Les Gasser},
  title={Noisy Preferential Attachment and Language Evolution},
  year={2006},
  pages={765-776},
  editor={Nolfi, S. and et al.},
  publisher={Springer Verlag},
  booktitle={SAB06},
  doi={10.1007/11840541_63},
  url={http://www.isrl.uiuc.edu/~amag/langev/paper/swarup06SAB.html}
}

HOME   ::  Conference List   ::   Conference Paper	Comments to: junwang4 you-know-at gmail.com	Last update: 10/27/09