| |
Abstract:
(Contributed Talk)
Fodor and Pylyshyn (1988) argue that Classical, but not
Connectionist, architectures support central features of
cognition, such as productivity, systematicity and
compositionality. In this paper, I examine the argument
concerning productive capacities. I argue that F&P
overestimate the abilities of Classical architectures and
underestimate the abilities of Connectionist architectures to
support productive capacities. I contend that, all in all,
Connectionist architectures do no worse than Classical
architectures in respect to productivity
|
