Saved in:
Bibliographic Details
Main Authors: He, Zihong, Lin, Weizhe, Zheng, Hao, Zhang, Fan, Jones, Matt W., Aitchison, Laurence, Xu, Xuhai, Liu, Miao, Kristensson, Per Ola, Shen, Junxiao
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.00489
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929670912475136
author He, Zihong
Lin, Weizhe
Zheng, Hao
Zhang, Fan
Jones, Matt W.
Aitchison, Laurence
Xu, Xuhai
Liu, Miao
Kristensson, Per Ola
Shen, Junxiao
author_facet He, Zihong
Lin, Weizhe
Zheng, Hao
Zhang, Fan
Jones, Matt W.
Aitchison, Laurence
Xu, Xuhai
Liu, Miao
Kristensson, Per Ola
Shen, Junxiao
contents With the rapid advancement of AI systems, their abilities to store, retrieve, and utilize information over the long term - referred to as long-term memory - have become increasingly significant. These capabilities are crucial for enhancing the performance of AI systems across a wide range of tasks. However, there is currently no comprehensive survey that systematically investigates AI's long-term memory capabilities, formulates a theoretical framework, and inspires the development of next-generation AI long-term memory systems. This paper begins by introducing the mechanisms of human long-term memory, then explores AI long-term memory mechanisms, establishing a mapping between the two. Based on the mapping relationships identified, we extend the current cognitive architectures and propose the Cognitive Architecture of Self-Adaptive Long-term Memory (SALM). SALM provides a theoretical framework for the practice of AI long-term memory and holds potential for guiding the creation of next-generation long-term memory driven AI systems. Finally, we delve into the future directions and application prospects of AI long-term memory.
format Preprint
id arxiv_https___arxiv_org_abs_2411_00489
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Human-inspired Perspectives: A Survey on AI Long-term Memory
He, Zihong
Lin, Weizhe
Zheng, Hao
Zhang, Fan
Jones, Matt W.
Aitchison, Laurence
Xu, Xuhai
Liu, Miao
Kristensson, Per Ola
Shen, Junxiao
Artificial Intelligence
With the rapid advancement of AI systems, their abilities to store, retrieve, and utilize information over the long term - referred to as long-term memory - have become increasingly significant. These capabilities are crucial for enhancing the performance of AI systems across a wide range of tasks. However, there is currently no comprehensive survey that systematically investigates AI's long-term memory capabilities, formulates a theoretical framework, and inspires the development of next-generation AI long-term memory systems. This paper begins by introducing the mechanisms of human long-term memory, then explores AI long-term memory mechanisms, establishing a mapping between the two. Based on the mapping relationships identified, we extend the current cognitive architectures and propose the Cognitive Architecture of Self-Adaptive Long-term Memory (SALM). SALM provides a theoretical framework for the practice of AI long-term memory and holds potential for guiding the creation of next-generation long-term memory driven AI systems. Finally, we delve into the future directions and application prospects of AI long-term memory.
title Human-inspired Perspectives: A Survey on AI Long-term Memory
topic Artificial Intelligence
url https://arxiv.org/abs/2411.00489