DeepColor: Reinforcement Learning optimizes information efficiency and well-formedness in color name partitioning
Paper i proceeding, 2018

As observed in the World Color Survey (WCS), some universal properties can be identified in color naming schemes over a large number of languages. For example, Regier, Kay, and Khetrapal (2007) and Regier, Kemp, and Kay (2015); Gibson et al. (2017) recently explained these universal patterns in terms of near optimal color partitions and information theoretic measures of efficiency of communication. Here, we introduce a computational learning framework with multi-agent systems trained by reinforcement learning to investigate these universal properties. We compare the results with Regier et al. (2007, 2015) and show that our model achieves excellent quantitative agreement. This work introduces a multi-agent reinforcement learning framework as a powerful and versatile tool to investi- gate such semantic universals in many domains and contribute significantly to central questions in cognitive science.

world color survey

reinforcement learning

color naming

Författare

Mikael Kågebäck

Chalmers, Data- och informationsteknik, Datavetenskap

Devdatt Dubhashi

Chalmers, Data- och informationsteknik, Data Science

Asad Sayeed

Göteborgs universitet

Proceedings of the 40th Annual Meeting of the Cognitive Science Society (CogSci)

40th Annual Meeting of the Cognitive Science Society (CogSci)
Madison, USA,

Mot kunskapsbaserad storskalig kunskapsutvinning ur svensk text

Vetenskapsrådet (VR), 2012-01-01 -- 2016-12-31.

Ämneskategorier

Datavetenskap (datalogi)

Mer information

Senast uppdaterat

2018-11-19