Recent advances in deep learning have allowed artificial intelligence (AI) to reach near human-level performance in many sensory, perceptual, linguistic, and cognitive tasks. There is a growing need, however, for novel, brain-inspired cognitive architectures. The Global Workspace Theory (GWT) refers to a large-scale system integrating and distributing information among networks of specialized modules to create higher-level forms of cognition and awareness. We argue that the time is ripe to consider explicit implementations of this theory using deep-learning techniques. We propose a roadmap based on unsupervised neural translation between multiple latent spaces (neural networks trained for distinct tasks, on distinct sensory inputs and/or modalities) to create a unique, amodal Global Latent Workspace (GLW). Potential functional advantages of GLW are reviewed, along with neuroscientific implications.

深度学习的最新进展使人工智能 (AI) 在许多感官、感知、语言和认知任务中达到接近人类水平的表现。然而，对新颖的、受大脑启发的认知架构的需求不断增长。全球工作空间理论（GWT）是指在专业模块网络之间集成和分发信息以创建更高层次的认知和意识形式的大规模系统。我们认为，考虑使用深度学习技术明确实现这一理论的时机已经成熟。我们提出了一个基于多个潜在空间（针对不同任务、不同感官输入和/或模态训练的神经网络）之间的无监督神经转换的路线图，以创建一个独特的、非模态的全局潜在工作空间（GLW）。