2025/01/06 by Samuel J. Gershman, Ila Fiete, Gershman, Samuel J. +3 · 5 voices · 8 citations
Computer Science · #Cognitive Science and Mapping #cs.AI #cs.LG #q-bio.NC
paper · pdf · doi:10.48550/arxiv.2501.02950
openalex publication_date 2025/01/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.