SRMU is a relevance-gated update rule with temporal decay for VSA streaming associative memories that filters redundant and stale information, yielding 12.6% higher memory similarity and 53.5% lower cumulative memory magnitude.
Olshausen, Yulia Sandamirskaya, Friedrich T
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
HyperSpace shows HRR and FHRR have comparable end-to-end runtime in spatial tasks despite FHRR's lower theoretical complexity per operation, with HRR using roughly half the memory.
citing papers explorer
-
SRMU: Relevance-Gated Updates for Streaming Hyperdimensional Memories
SRMU is a relevance-gated update rule with temporal decay for VSA streaming associative memories that filters redundant and stale information, yielding 12.6% higher memory similarity and 53.5% lower cumulative memory magnitude.
-
HyperSpace: A Generalized Framework for Spatial Encoding in Hyperdimensional Representations
HyperSpace shows HRR and FHRR have comparable end-to-end runtime in spatial tasks despite FHRR's lower theoretical complexity per operation, with HRR using roughly half the memory.