Massively-Parallel Inferencing for Natural language Understanding and Memory Retrieval in Structured Spreading-Activation Networks

Trent E. Lange

This paper provides an overview of ROBIN and REMIND, two structured connectionist models that provide a potential explanation for these abilities and that perform natural language understanding and episodic memory retrieval using parallel dynamic inferencing and constraint satisfaction.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.