Key-value memory in the brain
This addresses a foundational problem in memory modeling for researchers in psychology, neuroscience, and machine learning, offering a novel framework to resolve empirical puzzles.
The paper tackles the limitation of classical memory models that use the same representations for storage and retrieval, proposing key-value memory systems to optimize fidelity in storage and discriminability in retrieval. It reviews computational foundations, applications in machine learning, psychology, neuroscience, and biological implementations.
Classical models of memory in psychology and neuroscience rely on similarity-based retrieval of stored patterns, where similarity is a function of retrieval cues and the stored patterns. While parsimonious, these models do not allow distinct representations for storage and retrieval, despite their distinct computational demands. Key-value memory systems, in contrast, distinguish representations used for storage (values) and those used for retrieval (keys). This allows key-value memory systems to optimize simultaneously for fidelity in storage and discriminability in retrieval. We review the computational foundations of key-value memory, its role in modern machine learning systems, related ideas from psychology and neuroscience, applications to a number of empirical puzzles, and possible biological implementations.