Connectionist networks may be designed so that they can retrieve information from cues that are too vague to match a particular memory and provide a generalised picture of what is common to the memories that match the cues. Thus the network has the ability to generalise about classes of memories as part of its architecture.
Bechtel, W., & Abrahamsen, A. (1991). Connectionism and the mind: An introduction to parallel processing in networks. Cambridge, MA: Blackwell.
Functional Architecture | Symbolic Architecture | Parallel Distributed Processing Models | Content Addressable Memory | Graceful Degradation |
Contributed by J. Andrews, Dececmber, 1995