机器记忆智能——受人类记忆机制启发

工程（英文） ›› 2025, Vol. 55 ›› Issue (12) : 24 -35. DOI: 10.1016/j.eng.2025.01.012

机器记忆智能——受人类记忆机制启发

Qinghua Zheng ^a^,^b ,
Huan Liu ^a^,^b^,^* ,
Xiaoqing Zhang ^c^,^d ,
Caixia Yan ^a^,^b ,
Xiangyong Cao ^a^,^b ,
Tieliang Gong ^a^,^b ,
Yong-Jin Liu ^e ,
Bin Shi ^a^,^b ,
Zhen Peng ^a^,^b ,
Xiaocen Fan ^c^,^d ,
Ying Cai ^f ,
Jun Liu ^a^,^b

作者信息 +

Machine Memory Intelligence: Inspired by Human Memory Mechanisms

Qinghua Zheng ^a^,^b ,
Huan Liu ^a^,^b^,^* ,
Xiaoqing Zhang ^c^,^d ,
Caixia Yan ^a^,^b ,
Xiangyong Cao ^a^,^b ,
Tieliang Gong ^a^,^b ,
Yong-Jin Liu ^e ,
Bin Shi ^a^,^b ,
Zhen Peng ^a^,^b ,
Xiaocen Fan ^c^,^d ,
Ying Cai ^f ,
Jun Liu ^a^,^b

Author information +

文章历史 +

Received	Accepted	Published
2024-08-22	2025-01-24
Issue Date
2025-04-22

PDF

Abstract

Large models, exemplified by ChatGPT, have reached the pinnacle of contemporary artificial intelligence (AI). However, they are plagued by three inherent drawbacks: excessive training data and computing power consumption, susceptibility to catastrophic forgetting, and a deficiency in logical reasoning capabilities within black-box models. To address these challenges, we draw insights from human memory mechanisms to introduce “machine memory,” which we define as a storage structure formed by encoding external information into a machine-representable and computable format. Centered on machine memory, we propose the brand-new machine memory intelligence (M²I) framework, which encompasses representation, learning, and reasoning modules and loops. We explore the key issues and recent advances in the four core aspects of M²I, including neural mechanisms, associative representation, continual learning, and collaborative reasoning within machine memory. M²I aims to liberate machine intelligence from the confines of data-centric neural networks and fundamentally break through the limitations of existing large models, driving a qualitative leap from weak to strong AI.

关键词

Key words

Machine memory intelligence / Neural mechanism / Associative representation / Continual learning / Collaborative reasoning

引用本文

引用格式 ▾

Qinghua Zheng,Huan Liu,Xiaoqing Zhang,Caixia Yan,Xiangyong Cao,Tieliang Gong,Yong-Jin Liu,Bin Shi,Zhen Peng,Xiaocen Fan,Ying Cai,Jun Liu. 机器记忆智能——受人类记忆机制启发[J]. 工程（英文）, 2025, 55(12): 24-35 DOI:10.1016/j.eng.2025.01.012