论文标题
产品卡纳尔瓦机器：分解的贝叶斯记忆
Product Kanerva Machines: Factorized Bayesian Memory
论文作者
论文摘要
理想的认知灵感记忆系统将压缩和组织传入项目。 Kanerva Machine（Wu等，2018）是一种自然实现在线存储压缩的贝叶斯模型。但是，Kanerva机器的组织受到使用单个高斯随机矩阵存储的限制。在这里，我们介绍了产品Kanerva机器，该机器动态结合了许多较小的Kanerva机器。其层次结构为抽象不变特征提供了一种原则性的方式，并提供了比单坎纳尔机器的缩放和容量优势。我们表明，它可以表现出无监督的聚类，找到稀疏和组合分配模式，并发现空间调谐，以将简单图像分解为对象。
An ideal cognitively-inspired memory system would compress and organize incoming items. The Kanerva Machine (Wu et al, 2018) is a Bayesian model that naturally implements online memory compression. However, the organization of the Kanerva Machine is limited by its use of a single Gaussian random matrix for storage. Here we introduce the Product Kanerva Machine, which dynamically combines many smaller Kanerva Machines. Its hierarchical structure provides a principled way to abstract invariant features and gives scaling and capacity advantages over single Kanerva Machines. We show that it can exhibit unsupervised clustering, find sparse and combinatorial allocation patterns, and discover spatial tunings that approximately factorize simple images by object.
