TY - GEN
T1 - Holographic declarative memory
T2 - 2017 AAAI Fall Symposium
AU - Kelly, Matthew A.
AU - Reitter, David
N1 - Funding Information:
The authors gratefully acknowledge funding from NSF grants SES-1528409 and BCS-1734304.
Publisher Copyright:
Copyright © 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2017
Y1 - 2017
N2 - We explore replacing the declarative memory system of the ACT-R cognitive architecture with a distributional semantics model. ACT-R is a widely used cognitive architecture, but scales poorly to big data applications and lacks a robust model for learning association strengths between stimuli. Distributional semantics models can process millions of data points to infer semantic similarities from language data or to infer product recommendations from patterns of user preferences. We demonstrate that a distributional semantics model can account for the primacy and recency effects in free recall, the fan effect in recognition, and human performance on iterated decisions with initially unknown payoffs. The model we propose provides a flexible, scalable alternative to ACT-R's declarative memory at a level of description that bridges symbolic, quantum, and neural models of cognition.
AB - We explore replacing the declarative memory system of the ACT-R cognitive architecture with a distributional semantics model. ACT-R is a widely used cognitive architecture, but scales poorly to big data applications and lacks a robust model for learning association strengths between stimuli. Distributional semantics models can process millions of data points to infer semantic similarities from language data or to infer product recommendations from patterns of user preferences. We demonstrate that a distributional semantics model can account for the primacy and recency effects in free recall, the fan effect in recognition, and human performance on iterated decisions with initially unknown payoffs. The model we propose provides a flexible, scalable alternative to ACT-R's declarative memory at a level of description that bridges symbolic, quantum, and neural models of cognition.
UR - http://www.scopus.com/inward/record.url?scp=85044469245&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85044469245&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85044469245
T3 - AAAI Fall Symposium - Technical Report
SP - 382
EP - 387
BT - FS-17-01
PB - AI Access Foundation
Y2 - 9 November 2017 through 11 November 2017
ER -