Emergent communication of multimodal deep generative models based on Metropolis-Hastings naming game

• Published in: Frontiers in robotics and AI Vol. 10; p. 1290604
• Main Authors: Hoang, Nguyen Le, Taniguchi, Tadahiro, Hagiwara, Yoshinobu, Taniguchi, Akira
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Media S.A 31.01.2024
• Subjects: deep generative model; emergent communication; Metropolis-Hastings; multimodal; Robotics and AI; symbol emergence; variational autoencoder; naming game; Metropolis-Hastings; symbol emergence; multimodal; variational autoencoder; deep generative model; emergent communication

Deep generative models (DGM) are increasingly employed in emergent communication systems. However, their application in multimodal data contexts is limited. This study proposes a novel model that combines multimodal DGM with the Metropolis-Hastings (MH) naming game, enabling two agents to focus join...