A connectionist architecture for sequential symbolic domains

This report describes a connectionist architecture specifically intended for use in sequential domains requiring symbol manipulation. The architecture is based on a network formalism which differs from other connectionist networks developed for use in temporal/sequential domains. Units in this formalism are updated synchronously and retain partial activation between updates. They produce two output values: the standard sigmoidal function of the activity and its velocity. Activation flowing along connections can be gated by units. Well-behaved symbol buffers which leam complex assignment behavior can be constructed using gates. Full recurrence is supported. The network architecture, its underlying formalism, and its performance on an incremental parsing task requiring non-trivial dynamic behavior are presented. This research was funded by grants from ATR Interpreting Telephony Research Laboratories and the National Science Foundation under grant number EET-8716324. The views and conclusions contained in this document are those of the author and should not be interpreted as representing the official policies, either expressed or implied, of ATR, NSF, or the U.S. Government