arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2001.09485cs.LGstat.ML
收藏

基于全局工作空间理论的多模态数据融合

Multimodal Data Fusion based on the Global Workspace Theory

University College London(伦敦大学学院);Emotech Labs(Emotech实验室);Wellcome Centre for Human Neuroimaging, Institute of Neurology, University College London(伦敦大学学院神经病学研究所惠康人类神经影像中心)

Cong Bao, Zafeirios Fountas, Temitayo Olugbade, Nadia Bianchi-Berthouze

摘要:

我们提出了一种新的神经网络架构,命名为全球工作空间网络(GWN),它解决了多模态数据融合的动态和不确定性的挑战。我们的GWN是一个跨模态的注意力模型,并随着时间的推移而发展,其灵感来自认知科学领域的成熟的全球工作空间理论。GWN在区分疼痛患者和健康受试者方面的平均F1评分为0.92,在进一步分类患者的三个疼痛水平方面的平均F1评分为0.75,这两个评分都是基于从慢性疼痛患者和在不受约束的环境中进行不同类型运动的健康人中捕获的多模态RIPPain数据集。在这些任务中,GWN显著优于典型的合并级联融合方法。我们进一步提供了广泛的分析的GWN的行为和它的能力,以解决不确定性(隐藏的噪音)在多模态数据。

英文摘要:

We propose a novel neural network architecture, named the Global Workspace Network (GWN), which addresses the challenge of dynamic and unspecified uncertainties in multimodal data fusion. Our GWN is a model of attention across modalities and evolving through time, and is inspired by the well-established Global Workspace Theory from the field of cognitive science. The GWN achieved average F1 score of 0.92 for discrimination between pain patients and healthy participants and average F1 score = 0.75 for further classification of three pain levels for a patient, both based on the multimodal EmoPain dataset captured from people with chronic pain and healthy people performing different types of exercise movements in unconstrained settings. In these tasks, the GWN significantly outperforms the typical fusion approach of merging by concatenation. We further provide extensive analysis of the behaviour of the GWN and its ability to address uncertainties (hidden noise) in multimodal data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑