Dynamic binding in a neural network for shape recognition.

By John E. Hummel, Irving Biederman. 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

Rethinking eliminative connectionism. (1998, background): “…is currently instantiated) can then be encoded either by activating the variable and its current instantiation simultaneously in a common rhythm (Hummel & Biederman , 1992; Hummel & Holyoak, 1997; Shastri & Ajjanagadde, 1993), or, more generally, by attaching a shared identification code to…”
Evidence for knowledge-based category discrimination in infancy. (2002, background): “Part configuration is known to be highly relevant for object identification and categorization in adults as well as in children (Biederman, 1993; Hummel & Biederman, 1992; Madole & Cohen, 1995; Saiki & Hummel, 1996; Tversky & Hemenway, 1984; Younger, 1990; Younger & Cohen, 1986).”
A theory of the discovery and predication of relational concepts. (2008, methodology): “…shortly), because in order to appreciate what one instance of a relation has in common with another, the two situations must have something in common (specifically, the representational elements corresponding to the roles of the relation; Hummel & Biederman, 1992; Hummel & Holyoak, 1997).”
Relation learning in a neurocomputational architecture supports cross-domain transfer (2019, background): “se principles—and the models we have developed to instantiate them—account for over 100 major findings in human cognition, spanning at least seven domains: (a) shape perception and object recognition (16,29,30); (b) relational thinking (17,23,31-37), (c) learning structured representations (19, 38,3”
Models of object recognition (2000, background): “One of the most prominent models of this type is the 'recognition by components' (RBC) theor”