Full-text

URL: http://www.tech.plym.ac.uk/soc/research/...elosi-ijcnn99.ps.zip

Cached: PDF-94K    PS-302K    PS.gz-42K

SAVE AS an easy-to-recall long filename:

Filename format: author--year--title   PDF-94K    PS-42K    :: About GZip'd PS

Filename format: author--year--title--journal|proceedings|...--pages   PDF-94K    PS-42K

Related links

Web search: Google Web Search   ::   Google Scholar

Within this site: Cited by (1)    References (14)

Paper at a Glance

Evolution of Communication Using Symbol Combination in Populations of
Neural Networks
Angelo Cangelosi
Centre for Neural and Adaptive Systems
University of Plymouth (UK)
angelo@soc.plym.ac.uk

Abstract This paper uses a model of neural networks and genetic algorithms to simulate the evolution of communication in populations of evolving neural networks. It focuses on the emergence of simple forms of syntax, i.e. the combination of two symbols. The simulation task resembles Savage­ Rumbaugh & Rumbaugh's experiment [11] on ape language and symbol acquisition. The simulation results show the evolution and cultural transmission of languages based on combination of grounded symbols. The model is analyzed according to the issues of the symbol grounding and symbol acquisition problems.
1. Introduction Computational models using genetic algorithms, neural networks, and robotics, have been used for studying the evolution of language and communication [13]. Some models [2,10] have used neural networks and genetic algorithms for simulating the emergence of single­word languages. For example, organisms controlled by neural networks evolve a shared lexicon of two signals for naming two different types of food sources [2]. In other studies [4,12], agents use signal­meaning matrices for communication games. At the beginning of evolution all signals are randomly associated to all possible meanings. During evolution adaptive pressure only strengthens associations between one signal and one meaning. Communication games have also been used for originating meanings and language in groups of real robots [14]. Other modeling approaches have focused on the dynamics of syntax evolution. For example, the role of the Language Acquisition Device for learning artificial grammars has been studied [8]. This paper focuses on the emergence of simple forms of syntax. It will describe the simulation of the early stages of the evolution of syntax with the combination of two symbols. In particular, the ...

@inproceedings{cangelosi99evolutionOf,
  author={A. Cangelosi},
  title={Evolution of communication using combination of grounded symbols in populations of neural networks},
  year={1999},
  pages={4365-4368},
  address={Washington, DC},
  publisher={IEEE Press},
  booktitle={Proceedings of IJCNN99 International Joint Conference on Neural Networks (vol. 6)},
  url={http://www.isrl.uiuc.edu/~amag/langev/paper/cangelosi99evolutionOf.html}
}

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