Trent E. Lange

TL;DR: Connectionist models have had problems representing and applying general knowledge rules that specifically require variables, and this variable binding problem has barred them from performing the high-level knowledge operations needed to solve this problem.

TL;DR: The authors found that both retrieval competition and structural consistency influence reminding, with the latter tending to be greater in the competition condition, while the former tends to be more dominant in the non-competition condition.

TL;DR: All experiments supported the hypothesis that human memory is sensitive to remote analogical similarity and the implications for memory models require the development of formal models that quantify factors relevant to reminding performance.

TL;DR: REMIND is a model that performs both episodic memory retrieval and language understanding with a single spreading-activation mechanism, which potentially explains how the explicit indexing of case-based reasoning models can be eliminated, while retaining its benefits as an emergent property of the comprehension process.

TL;DR: The localist network model, ROBIN (ROle Binding and Inferencing Network), uses signature activations to robustly represent schemata role-bindings and thus perform the inferencing, plan/goal analysis, schema instantiation, word-sense disambiguation, and dynamic re-interpretation portions of the natural language understanding process.