Neural modeling of episodic memory: Encoding, retrieval, and forgetting

• Main Authors: WANG, Wenwen, SUBAGDJA, Budhitama, TAN, Ah-hwee, STARZYK, Janusz A.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2012
• Subjects: episodic memory; agent; ART based network; hierarchical structure; memory robustness; forgetting; Unreal Tournament; Databases and Information Systems; Programming Languages and Compilers; Software Engineering
• Online Access: https://ink.library.smu.edu.sg/sis_research/5202; https://ink.library.smu.edu.sg/context/sis_research/article/6205/viewcontent/Neural_Modeling_of_Episodic_Memory___TNNLS_2012_Preprint.pdf
• Institution: Singapore Management University

This paper presents a neural model that learns episodic traces in response to a continuous stream of sensory input and feedback received from the environment. The proposed model, based on fusion Adaptive Resonance Theory (fusion ART) network, extracts key events and encodes spatio-temporal relations between events by creating cognitive nodes dynamically. The model further incorporates a novel memory search procedure, which performs parallel search of stored episodic traces continuously. Combined with a mechanism of gradual forgetting, the model is able to achieve a high level of memory performance and robustness, while controlling memory consumption over time. We present experimental studies, where the proposed episodic memory model is evaluated based on the memory consumption for encoding events and episodes as well as recall accuracy using partial and erroneous cues. Our experimental results show that: (1) The model produces highly robust performance in encoding and recalling events and episodes even with incomplete and noisy cues; (2) The model provides an enhanced performance in noisy environment due to the process of forgetting; (3) Compared with prior models of spatio-temporal memory, our model shows a higher tolerance towards noise and errors in the retrieval cues.