arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.02849cond-mat.dis-nn
收藏

密集联想记忆中的容差与突触噪声

Tolerance versus synaptic noise in dense associative memories

Elena Agliari, Giordano De Marzo

摘要:

联想神经网络的检索能力可能会受到不同类型的噪声的影响:快速噪声(使神经元更容易失败),缓慢噪声(源于存储记忆之间的干扰)和突触噪声(由于学习或存储阶段可能存在的缺陷)。在这项工作中,我们认为密集的联想神经网络,神经元可以相互作用的$p$ -plets,在没有快速噪声,我们调查的相互作用缓慢和突触噪声。特别是,利用联想神经网络和受限玻尔兹曼机之间的对偶性,我们分析了损坏的信息,不完美的学习和存储错误的影响。对于$p=2$(对应于Hopfield模型),如果记忆$K$的数量与网络大小成比例,则任何突触噪声源都可以中断检索。对于$p>2$,在相对低负荷的状态$K \sim N$中,突触噪声被容忍到一定的界限,这取决于结构的密度。

英文摘要:

The retrieval capabilities of associative neural networks can be impaired by different kinds of noise: the fast noise (which makes neurons more prone to failure), the slow noise (stemming from interference among stored memories), and synaptic noise (due to possible flaws during the learning or the storing stage). In this work we consider dense associative neural networks, where neurons can interact in $p$-plets, in the absence of fast noise, and we investigate the interplay of slow and synaptic noise. In particular, leveraging on the duality between associative neural networks and restricted Boltzmann machines, we analyze the effect of corrupted information, imperfect learning and storing errors. For $p=2$ (corresponding to the Hopfield model) any source of synaptic noise breaks-down retrieval if the number of memories $K$ scales as the network size. For $p>2$, in the relatively low-load regime $K \sim N$, synaptic noise is tolerated up to a certain bound, depending on the density of the structure.

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。

↑