Neural Modeling of Episodic Memory: Encoding, Retrieval, and Forgetting

• Published in: IEEE transaction on neural networks and learning systems Vol. 23; no. 10; pp. 1574 - 1586
• Main Authors: Wenwen Wang, Subagdja, B., Ah-Hwee Tan, Starzyk, J. A.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.10.2012; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation models; Adaptive resonance theory-based network; agent; Animals; Applied sciences; Artificial intelligence; Brain - physiology; Cognition - physiology; Combinatorics; Combinatorics. Ordered structures; Computational modeling; Computer science; control theory; systems; Computer Simulation; Connectionism. Neural networks; Encoding; episodic memory; Exact sciences and technology; forgetting; Graph theory; hierarchical structure; Humans; Information retrieval. Graph; Mathematics; Memory and file management (including protection and security); Memory management; Memory organisation. Data processing; memory robustness; Memory, Episodic; Mental Recall - physiology; Models, Neurological; Nerve Net - physiology; Neuronal Plasticity - physiology; Robustness; Sciences and techniques of general use; Software; Studies; Subspace constraints; Theoretical computing; unreal Tournament; Vectors; Forgetting; High performance; Memory retrieval; agent; Adaptive resonance theory; hierarchical structure; Graph theory; Neural network; Modeling; Cognitive theory; Storage management; Unreal Tournament; Robustness; memory robustness; Hierarchical system; Adaptive resonance theory-based network; Time analysis; Episodic memory; Tournament
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2012.2208477

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 (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 a continuous parallel search of stored episodic traces. 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 enhanced performance in a noisy environment due to the process of forgetting; and 3) compared with prior models of spatio-temporal memory, our model shows a higher tolerance toward noise and errors in the retrieval cues.