Abstract
I introduce a novel associative memory model named Correlated Dense Associative Memory (CDAM), which integrates both auto- and hetero-association in a unified framework for continuous-valued memory patterns. Employing an arbitrary graph structure to semantically link memory patterns, CDAM is theoretically and numerically analysed, revealing four distinct dynamical modes: auto-association, narrow hetero-association, wide hetero-association, and neutral quiescence. Drawing inspiration from inhibitory modulation studies, I employ anti-Hebbian learning rules to control the range of hetero-association, extract multi-scale representations of community structures in graphs, and stabilise the recall of temporal sequences. Experimental demonstrations showcase CDAM's efficacy in handling real-world data, replicating a classical neuroscience experiment, performing image retrieval, and simulating arbitrary finite automata.
Abstract (translated)
我提出了一种名为关联密度关联记忆(CDAM)的新颖的联想记忆模型,将自组织和异组织关联整合在一个统一的框架中,以处理连续值记忆模式。利用任意图结构将记忆模式语义链接起来,CDAM从理论和数值上进行研究,揭示了四种不同的动态模式:自组织、狭窄异组织关联、宽异组织关联和中性休眠。从抑制性调节研究的灵感中,我使用反Hebbian学习规则来控制异组织关联的范围,提取图社区结构的 multi-scale 表示,并稳定地回忆时间序列。实验演示展示了CDAM在处理现实世界数据、复制经典神经科学研究、进行图像检索和模拟任意有限自动机方面的有效性。
URL
https://arxiv.org/abs/2404.07123