Open Peer Commentary Edelman: Representation of similarities
Representations need self-organizing top-down expectations to fit a changing world
Stephen Grossberg a1 a1 Department of Cognitive and Neural Systems, Boston University, Boston, MA 02215
“Chorus embodies an attempt to find out how far a mostly
bottom-up approach to representation can be taken.” Models that
embody both bottom-up and top-down learning have stronger
computational properties and explain more data about representation
than feedforward models do.