Presentation
Beyond Frequency and Recency: An Entropy-Based Extension for Modeling Memory Retrieval in Dynamic Environments
DescriptionThis study extends the ACT-R base-level learning equation by incorporating environmental uncertainty, observation duration, and individual learning patterns to better model human memory retrieval in dynamic, multi-object environments. We hypothesize that retrieval efficiency depends not only on frequency and recency of interactions but also on scene entropy, time spent observing, and a learning pattern parameter (α). Using a household task scenario in the AI2-THOR simulator, we analyzed search times as proxies for memory access. Our modified equation integrates entropy to reflect visual uncertainty, scales decay by observation duration, and includes α to capture task-specific learning dynamics. Results from eight participants revealed distinct retrieval patterns (e.g., Increasing–Decreasing vs. Decreasing–Increasing search times) related to prior experience. Compared to the original ACT-R model (MAE = 0.3135, correlation = 0.4568), our modified equation achieved a lower average MAE of 0.2629 and a higher correlation of 0.6126 with observed behavior, demonstrating improved predictive accuracy. These findings offer a stronger foundation for modeling memory retrieval and have implications for adaptive user interfaces, training systems, and assistive agents that rely on understanding human memory performance in visually complex settings.
Event Type
Industry/Practitioner Content
Lecture
TimeWednesday, October 15th11:30am - 11:50am CDT
LocationGrand A
Cognitive Engineering & Decision Making