How does the Mind store Information?
This addresses the conceptual and algorithmic challenge of information storage in the mind, but it is incremental as it builds directly on prior recursive sketching methods.
The paper tackles the problem of how the mind stores information by proposing a memory architecture based on recursive sketching, which uses concise sketches to organize and index information, forming an implicit knowledge graph for retrieving related past information during event processing.
How we store information in our mind has been a major intriguing open question. We approach this question not from a physiological standpoint as to how information is physically stored in the brain, but from a conceptual and algorithm standpoint as to the right data structures to be used to organize and index information. Here we propose a memory architecture directly based on the recursive sketching ideas from the paper "Recursive Sketches for Modular Deep Networks", ICML 2019 (arXiv:1905.12730), to store information in memory as concise sketches. We also give a high level, informal exposition of the recursive sketching idea from the paper that makes use of subspace embeddings to capture deep network computations into a concise sketch. These sketches form an implicit knowledge graph that can be used to find related information via sketches from the past while processing an event.