Connectionism, Learning and Meaning

There is an apparent anomaly in the notion that connectionism, which is fundamentally a new technology, has considerable philosophical significance. Nonetheless, connectionism has been widely viewed as having implications for symbol grounding, notions of structured representation and compositionality, as well as the issue of nativism. In this paper, we consider each of these issues in detail, and find that the current state of connectionism does not warrant the magnitude of many of the philosophical conclusions drawn from it. We argue that connectionist models are no more “grounded” than their classical counterparts. In addition, since connectionist representations typically are ascribed content through semantic interpretation based on correlation, connectionism is prone to a number of well-known philosophical problems facing any kind of correlational semantics. However, we suggest that philosophy may be ill-advised to ignore the development of connectionism, particularly if connectionist systems prove to be able to learn to handle structured representations. keywords: Connectionism, computation, semantics, learning, representation, compositionality, nativism. running heading: Connectionism and Meaning. ∗The order of authorship is arbitrary. Requests for reprints should be send to the first author (phone no. +44 (0)31 650 4420). Morten Christiansen is supported by award No. V910048 from the Danish Research Academy. Nick Chater is partially supported by grant No. MRC FPG 9024590 from the Joint Councils Initiative in Cognitive Science/HCI.