Gary Marcus

[S]ymbol-manipulation consists of three... hypotheses... [M]ind [1] represents abstract relationships between variables... [2] has a system of recursively structured representations... [3] distinguishes between mental representations of individuals and mental representations of kinds. ...[T]hese can stand or fall separately. Any given model... can be consistent with one subset of the... hypotheses... or all...

The problem is that... connectionism has become synonymous with... back-propogation. ...[T]hat... type of network... occupies... a small corner in the... space of possible network models. ...[A]dequate models of most likely lie in a less explored part of the space...

I am not an anti-connectionist; I am opposed only to a... subset of possible connectionist models.

[S]ymbol manipulating models... use logical functions like AND and OR... [T]hose functions can easily be built in—or, implemented in—connectionist nodes.

... taken... broadly... could help us answer... what the mind's basic building blocks are and how those... could be implemented in the brain.

[C]onnectionism... encompasses models that have sought to explain how symbol-manipulation can be implemented in a neural substrate...

I have often encountered audiences that... want me to prove... mind manipulates symbols. ...I can do no such thing. At most... symbol-manipulation is consistent with the facts and... the alternatives thus far... are inadequate.

I focus on... multilayer perceptrons because these are... discussed when researchers consider the relation between connectionism and symbol-manipulation.