https://scholars.lib.ntu.edu.tw/handle/123456789/571751
標題: | A Brain-Inspired, Self-Organizing Episodic Memory Model for a Memory Assistance Robot | 作者: | Yang C Gamborino E Fu L YU-LING CHANG LI-CHEN FU |
關鍵字: | Brain modeling; Computational modeling; Episodic Memory Assistance; Graphical Model; Health Care Robot; Mathematical model; Memory Model; Reinforcement Learning.; Robots; Semantics; Senior citizens; Subspace constraints | 公開日期: | 2022 | 卷: | 14 | 期: | 2 | 起(迄)頁: | 617-628 | 來源出版物: | IEEE Transactions on Cognitive and Developmental Systems | 摘要: | This paper discusses the implementation of a brain-inspired episodic memory model, which provides memory assistance and tackles the modern public issue of memory impairment embedded as an end-to-end system on the robot companion, Pepper. Based on Fusion ART (Adaptive Resonance Theory), the proposed model can observe and memorize the content of daily events in five aspects: people, activities, times, places, and objects. The model is based on the human memory pipeline, containing a working memory and a two-layer long-term memory model, which can effectively merge, cluster, and summarize past memories based on their context and relevance in a self-organizing manner. When providing memory assistance, the robot can analyze a user query and find the best matching memory cluster to generate verbal cues to stimulate recalling of the target event. Moreover, using reinforcement learning, the robot eventually learns the most effective mapping of cue types to event type through social interaction. Experiments show the feasibility of the proposed model, which can handle episodic events with elasticity and stability. Moreover, there is evidence that the robot is able to provide robust memory assistance from knowledge obtained through previous observations, with 99% confidence, intervals in the participants’ mean recall percentage of the events increases 19.63% after receiving memory assistance from the robot. IEEE |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85101750130&doi=10.1109%2fTCDS.2021.3061659&partnerID=40&md5=df3bc52660f99d76a441588598d2cb59 https://scholars.lib.ntu.edu.tw/handle/123456789/571751 |
ISSN: | 23798920 | DOI: | 10.1109/TCDS.2021.3061659 | SDG/關鍵字: | Brain; Reinforcement learning; Adaptive resonance theory; End-to-end systems; Episodic events; Episodic memory; Long term memory; Memory clusters; Robot companion; Social interactions; Robots |
顯示於: | 心理學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。