arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0707.0565cond-mat.dis-nncond-mat.other
收藏

无信息的记忆将占上风:相关表征的存储及其后果

Uninformative memories will prevail: the storage of correlated representations and its consequences

Emilio Kropff, Alessandro Treves

摘要:

自联想网络是在80年代提出的,作为大脑记忆功能的简化模型,使用具有赫布可塑性的递归连接来存储以后可以回忆的神经活动模式。这种类型的计算被认为发生在海马的CA3区域和皮层的几个层次。这些模型的弱点之一是它们显然无法存储相关的活动模式。然而,我们发现,一个小的和生物学上合理的修改“学习规则”(关联到每个神经元的可塑性阈值,反映其受欢迎程度),使网络能够处理相关性。我们研究了由此产生的记忆的稳定性(就其对神经元或突触损伤的抵抗力而言),发现了自联想网络的一个新特性:并非所有的记忆都是同样强大的,并且信息量最大的也是对损伤最敏感的。我们将这些结果与语义记忆患者的类别特异性效应相关,其中与“非生物”相关的概念通常比与“生物”相关的概念更能抵抗脑损伤,这种现象被怀疑植根于皮层中概念表征之间的相关性。

英文摘要:

Autoassociative networks were proposed in the 80's as simplified models of memory function in the brain, using recurrent connectivity with hebbian plasticity to store patterns of neural activity that can be later recalled. This type of computation has been suggested to take place in the CA3 region of the hippocampus and at several levels in the cortex. One of the weaknesses of these models is their apparent inability to store correlated patterns of activity. We show, however, that a small and biologically plausible modification in the `learning rule' (associating to each neuron a plasticity threshold that reflects its popularity) enables the network to handle correlations. We study the stability properties of the resulting memories (in terms of their resistance to the damage of neurons or synapses), finding a novel property of autoassociative networks: not all memories are equally robust, and the most informative are also the most sensitive to damage. We relate these results to category-specific effects in semantic memory patients, where concepts related to `non-living things' are usually more resistant to brain damage than those related to `living things', a phenomenon suspected to be rooted in the correlation between representations of concepts in the cortex.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑