I wish to thank Robert Cummins, Paul Teller, and an anonymous referee for helpful discussions of the issues addressed in this paper.
Program Execution in Connectionist Networks
Version of Record online: 31 AUG 2005
Mind & Language
Volume 20, Issue 4, pages 448–467, September 2005
How to Cite
Roth, M. (2005), Program Execution in Connectionist Networks. Mind & Language, 20: 448–467. doi: 10.1111/j.0268-1064.2005.00295.x
- Issue online: 31 AUG 2005
- Version of Record online: 31 AUG 2005
Abstract: Recently, connectionist models have been developed that seem to exhibit structure-sensitive cognitive capacities without executing a program. This paper examines one such model and argues that it does execute a program. The argument proceeds by showing that what is essential to running a program is preserving the functional structure of the program. It has generally been assumed that this can only be done by systems possessing a certain temporal-causal organization. However, counterfactual-preserving functional architecture can be instantiated in other ways, for example geometrically, which are realizable by connectionist networks.