Attention Approximates Sparse Distributed Memory.

Trenton Bricken Cengiz Pehlevan

Published in: NeurIPS (2021)

Keyphrases

distributed memory
shared memory
parallel implementation
fine grain
multiprocessor systems
ibm sp
scientific computing
parallel architecture
parallel computers
matrix multiplication
data parallelism
parallel machines
multithreading
multi processor
probabilistic model
computer vision
fine grained
information systems