Associative memory plays an important role in human intelligence and its
mechanisms have been linked to attention in machine learning. While the machine
learning community's interest in associative memories has recently been
rekindled, most work has focused on memory recall ($read$) over memory learning
($write$). In this paper, we present BayesPCN, a hierarchical associative
memory capable of performing continual one-shot memory writes without
meta-learning. Moreover, BayesPCN is able to gradually forget past observations
($forget$) to free its memory. Experiments show that BayesPCN can recall
corrupted i.i.d. high-dimensional data observed hundreds to a thousand
``timesteps'' ago without a large drop in recall ability compared to the
state-of-the-art offline-learned parametric memory models.

本文提出 BayesPCN，一个具有层级结构的关联记忆，能够进行连续的一次性记忆写入，而无需元学习，并能逐渐遗忘过去的观察结果，以释放存储空间。实验表明，BayesPCN 能够回忆起数百到数千个时间步长以前观察到的损坏的高维数据，与现有的线下学习的参数记忆模型相比，不会出现大幅下降的召回能力。