Open AccessA 8.93-TOPS/W LSTM Recurrent Neural Network Accelerator Featuring Hierarchical Coarse-Grain Sparsity With All Parameters Stored On-Chip
Author(s) -
Deepak Kadetotad,
Visar Berisha,
Chaitali Chakrabarti,
Jae-sun Seo
Publication year - 2019
Publication title -
ieee solid-state circuits letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.588
H-Index - 10
ISSN - 2573-9603
DOI - 10.1109/lssc.2019.2936761
Subject(s) - computer science , recurrent neural network , block (permutation group theory) , chip , artificial neural network , computer hardware , timit , tops , energy (signal processing) , algorithm , artificial intelligence , materials science , mathematics , telecommunications , geometry , statistics , spinning , hidden markov model , composite material