A Distributed Learning Algorithm for Communication Development
Complex Systems · 2024
DOI: 10.25088/complexsystems.14.4.315 ↗Kurz gefasst
Fachartikel in der Zeitschrift Complex Systems, 2024. Verfasst von Edwin D. de Jong und 1 weiteren Autor:innen.
Abstract (Originalsprache)
We study the question of how a local learning algorithm, executed by multiple distributed agents, can lead to a global system of communication. First, the notion of a perfect communication system is defined. Next, two measures of communication system quality are specified. It is shown that maximization of these measures leads to perfect communication production. Based on this principle, local adaptation rules for communication development are constructed. The resulting stochastic algorithm is validated in computational experiments. Empirical analysis indicates that a mild degree of stochasticity is instrumental in reaching states that correspond to accurate communication.
Zitieren
APA
Jong, E. D. D., & Steels, L. (2024). A Distributed Learning Algorithm for Communication Development. Complex Systems. https://doi.org/10.25088/complexsystems.14.4.315
Vancouver
Jong EDD, Steels L. A Distributed Learning Algorithm for Communication Development. Complex Systems. 2024. doi:10.25088/complexsystems.14.4.315
BibTeX
@article{Jong2024,
author = {Jong, Edwin D. de and Steels, Luc},
title = {A Distributed Learning Algorithm for Communication Development},
journal = {Complex Systems},
year = {2024},
doi = {10.25088/complexsystems.14.4.315}
}
EUVIMED