On Variable Binding in Connectionist Networks

By Ron Sun. 1992

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

On the Binding Problem in Artificial Neural Networks (2020, background): “Indeed, the search for an adequate mechanism for binding (in one form or another) is a longstanding problem, not just in neuroscience and cognitive psychology, but also in machine learning (Smolensky, 1987, 1988; Sun, 1992).”
SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition (2020, background): “It may also enable visual variable binding (Sun, 1992) for reasoning and causal inference over the relationships between the objects and agents in a scene.”
Rethinking eliminative connectionism. (1998, background): “Similar arguments have been made within less radical quarters of the connectionist community (Barnden, 1984, 1992; Dyer, 1995; Shastri & Ajjanagadde, 1993; Sun, 1992; Touretzky, 1991; Touretzky & Hinton, 1985).”
Incubation, insight, and creative problem solving: a unified theory and a connectionist model. (2010, background): “For instance, it was argued in Sun et al. (2005) that it was not necessary to select upfront”
From implicit skills to explicit knowledge: a bottom-up model of skill learning (2001, methodology): “For more complex rule forms including predicate rules and variable binding, see Sun (1992).”
Scene segmentation by spike synchronization in reciprocally connected visual areas. II. Global assemblies and synchronization on larger space and time scales (2002, background): “This problem is clearly related to the ‘binding problem’ discussed extensively in Knoblauch and Palm (2002) and also to the problem of ‘variable binding’ in neural networks (see Shastri and Ajjanagadde 1993; Sun 1992; Fukushima 1988).”