Global Workspace (computational feature)

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Global Structureconcept0.744
  The large-scale organizational pattern of a system whose preservation defines wholeness-preserving transformations
• A system with high integrated information but no goals, or a global workspace broadcasting non-evaluative content, would not be conscious on the present accountclaim0.744
  Point of genuine disagreement with IIT and GWT
• GWT-3: Global broadcast: availability of information in the workspace to all modulesconcept0.733
  Indicator: global broadcast to all modules.
• Information bottleneck in workspaceconcept0.728
  Limited capacity of the workspace relative to the sum of module capacities.
• Space is a material whose most important feature is its capacity to form centers.claim0.727
  Reiteration of a key premise from Book 1 within the new metaphysical framework.
• The features are often organized in geometrically-related clusters that share a semantic relationship.claim0.724
  Decoder cosine similarity maps onto concept similarity.
• The resulting features are highly abstract: multilingual, multimodal, and generalizing between concrete and abstract references.claim0.721
  Features respond to concepts across languages and in images, not just text.
• Geometry of featuresconcept0.720
  Research thread within About Blank concerning the structure and relational properties of neural network feature representations; covariance pooling tangentially supports this thread.