Domain learning naming game for color categorization.

Doujie Li,Zhongyan Fan,Wallace K S Tang

doi:10.1371/journal.pone.0188164

Abstract

Naming game simulates the evolution of vocabulary in a population of agents. Through pairwise interactions in the games, agents acquire a set of vocabulary in their memory for object naming. The existing model confines to a one-to-one mapping between a name and an object. Focus is usually put onto name consensus in the population rather than knowledge learning in agents, and hence simple learning model is usually adopted. However, the cognition system of human being is much more complex and knowledge is usually presented in a complicated form. Therefore, in this work, we extend the agent learning model and design a new game to incorporate domain learning, which is essential for more complicated form of knowledge. In particular, we demonstrate the evolution of color categorization and naming in a population of agents. We incorporate the human perceptive model into the agents and introduce two new concepts, namely subjective perception and subliminal stimulation, in domain learning. Simulation results show that, even without any supervision or pre-requisition, a consensus of a color naming system can be reached in a population solely via the interactions. Our work confirms the importance of society interactions in color categorization, which is a long debate topic in human cognition. Moreover, our work also demonstrates the possibility of cognitive system development in autonomous intelligent agents.

Highlights

Naming game (NG) model describes the interaction of two agents, targeting for knowledge transfer [1]
We propose a new learning process, called Domain Learning Naming Game, based on the understanding of human perception and cognition
The domain learning naming game is conducted in a population of agents with connectivity defined by an underlying topology, where each agent is as described before

Summary

Introduction

Naming game (NG) model describes the interaction of two agents, targeting for knowledge transfer [1]. A lot of research work have been carried out to study how the agent selection process, both for the speaker and the hearer, may affect the reaching of consensus and the success rate of the games [3,4,5,6,7,8]. A bidirectional way of learning is suggested for MNG in [17] If it is a success, all names common in both the speaker and the hearer are kept. We here question whether it is possible for agents to autonomously develop a color naming system together with the category of colors solely based on interactions, without any pre-requisition in the learning process. We propose a new learning process, called Domain Learning Naming Game, based on the understanding of human perception and cognition.

Methods

Design of the game

Results