Product Kanerva Machines: Factorized Bayesian Memory
This work addresses memory organization in cognitive systems, offering a hierarchical approach for better feature abstraction and scaling, though it appears incremental as it builds directly on the Kanerva Machine.
The authors tackled the limited organization of the Kanerva Machine by introducing the Product Kanerva Machine, which dynamically combines smaller Kanerva Machines to achieve unsupervised clustering, sparse allocation patterns, and factorization of images by object.
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.