Program Execution in Connectionist Networks
Martin Roth · Mind & Language · 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.