首页|Study Results from Ritsumeikan University in the Area of Robotics and Artificial Intelligence Published (Emergent communication of multimodal deep generative models based on Metropolis-Hastings naming game)
Study Results from Ritsumeikan University in the Area of Robotics and Artificial Intelligence Published (Emergent communication of multimodal deep generative models based on Metropolis-Hastings naming game)
扫码查看
点击上方二维码区域,可以放大扫码查看
原文链接
NETL
NSTL
Frontiers Media Sa
Investigators publish new report on robotics and artificial intelligence. According to news originating from Shiga, Japan, by NewsRx correspondents, research stated, “Deep generative models (DGM) are increasingly employed in emergent communication systems.” The news journalists obtained a quote from the research from Ritsumeikan University: “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 jointly on a shared subject and develop common vocabularies. The model proves that it can handle multimodal data, even in cases of missing modalities. Integrating the MH naming game with multimodal variational autoencoders (VAE) allows agents to form perceptual categories and exchange signs within multimodal contexts. Moreover, fine-tuning the weight ratio to favor a modality that the model could learn and categorize more readily improved communication. Our evaluation of three multimodal approaches mixture-of-experts (MoE), product-of-experts (PoE), and mixture-of-product-of-experts (MoPoE)-suggests an impact on the creation of latent spaces, the internal representations of agents.” According to the news reporters, the research concluded: “Our results from experiments with the MNIST + SVHN and Multimodal165 datasets indicate that combining the Gaussian mixture model (GMM), PoE multimodal VAE, and MH naming game substantially improved information sharing, knowledge formation, and data reconstruction.”
Ritsumeikan UniversityShigaJapanAsiaMachine LearningRobotics and Artificial Intelligence