MnnFast: A Fast and Scalable System Architecture for Memory-Augmented Neural Networks

Memory-augmented neural networks are getting more attention from many researchers as they can make an inference with the previous history stored in memory. Especially, among these memory-augmented neural networks, memory networks are known for their huge reasoning power and capability to learn from...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	2019 ACM/IEEE 46th Annual International Symposium on Computer Architecture (ISCA) s. 250 - 263
Hlavní autoři:	Jang, Hanhwi, Kim, Joonsung, Jo, Jae-Eon, Lee, Jaewon, Kim, Jangwoo
Médium:	Konferenční příspěvek
Jazyk:	angličtina
Vydáno:	ACM 01.06.2019
Témata:	Accelerator Algorithm-Hardware Co-Design Architecture Attention-based Neural Networks Bandwidth Cognition Computation/Dataflow Optimization Field programmable gate arrays Graphics processing units Hardware Machine Learning Machine learning algorithms Memory management Memory Networks Neural networks Optimization Parallel Algorithm Systems architecture
ISSN:	2575-713X
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!