Open Peer Commentary Edelman: Representation of similarities
How to combine interpolation with feedback?
Guenther Palm a1 a1 Department of Neural Information Processing, University of Ulm, D-89069 Ulm, Germany
The Chorus representation is a sparse, similarity-preserving
representation achieved by a feedforward neural network. Hence it
is probably better suited for interpolation than for categorization.
This commentary raises the question of how to combine categorization
with interpolation, whether feedforward networks can be reasonable
models for parts of the cerebral cortex, and whether people can
perform more than one interpolation at a time.