Deep Learning and the Global Workspace Theory

2020/12/04 by Rufin VanRullen, Ryota Kanai, VanRullen, Rufin +1 · 9 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Engineering · Neuroscience · Psychology · #Advanced Memory and Neural Computing #Amodal perception #Artificial Intelligence (cs.AI) #Artificial intelligence #Artificial neural network #Cognition #Cognitive science #Computer science #Deep learning #Deep neural networks #Embodied and Extended Cognition #FOS: Biological sciences #FOS: Computer and information sciences #Human–computer interaction #Modalities #Neural and Evolutionary Computing (cs.NE) #Neural dynamics and brain function #Neurons and Cognition (q-bio.NC) #Neuroscience #Perception #Psychology #Robot #Workspace #cs.AI #cs.NE #q-bio.NC

paper · pdf · doi:10.48550/arxiv.2012.10390

This version with improved text and figures

openalex publication_date 2020/12/04 · arxiv created 2021/02/20 · arxiv updated 2021/02/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Recent advances in deep learning have allowed Artificial Intelligence (AI) to reach near human-level performance in many sensory, perceptual, linguistic or cognitive tasks. There is a growing need, however, for novel, brain-inspired cognitive architectures. The Global Workspace theory 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.

Citations

• A cognitive architecture that combines internal simulation with a global workspace
• Ongoing Spontaneous Activity Controls Access to Consciousness: A Neuronal Model for Inattentional Blindness
• The perceptron: A probabilistic model for information storage and organization in the brain.
• Universal Intelligence: A Definition of Machine Intelligence
• On a confusion about a function of consciousness
• The Consciousness Prior
• Text-to-Image-to-Text Translation using Cycle Consistent Adversarial Networks
• Recurrent World Models Facilitate Policy Evolution
• Deep learning
• A deep learning framework for neuroscience
• Conscious Processing and the Global Neuronal Workspace Hypothesis
• Information Closure Theory of Consciousness

Cited by

• Interoceptive machine framework: Toward interoception-inspired regulatory architectures in artificial intelligence
• AI Consciousness and Existential Risk
• Finding Similar Objects and Active Inference for Surprise in Numenta Neocortex Model
• Attention Schema-based Attention Control (ASAC): A Cognitive-Inspired Approach for Attention Management in Transformers
• On the utility of toy models for theories of consciousness
• MIRROR: Converging Cognitive Principles as Computational Mechanisms for AI Reasoning
• Hypothesis on the Functional Advantages of the Selection-Broadcast Cycle Structure: Global Workspace Theory and Dealing with a Real-Time World
• MAIN-VLA: Modeling Abstraction of Intention and eNvironment for Vision-Language-Action Models
• The Ignition Index: Measuring Global Workspace Dynamics in Language Models
• Continual learning for rotating machinery fault diagnosis with cross-domain environmental and operational variations

Related

• Coordination Among Neural Modules Through a Shared Global Workspace
• A Unified Geometric Space Bridging AI Models and the Human Brain
• Towards a neural architecture of language: Deep learning versus logistics of access in neural architectures for compositional processing
• Multimodal Data Fusion based on the Global Workspace Theory
• Deep Learning for Cognitive Neuroscience