|
gptkbp:instanceOf
|
gptkb:computer_scientist
|
|
gptkbp:almaMater
|
gptkb:Stanford_University
gptkb:Tsinghua_University
|
|
gptkbp:awardReceived
|
gptkb:NSF_CAREER_Award
gptkb:Google_Faculty_Research_Award
gptkb:MIT_Technology_Review_Innovators_Under_35
gptkb:Amazon_Research_Award
Facebook Faculty Research Award
NVIDIA Pioneer Research Award
|
|
gptkbp:department
|
gptkb:Electrical_Engineering_and_Computer_Science
|
|
gptkbp:doctoralAdvisor
|
William J. Dally
|
|
gptkbp:employer
|
gptkb:MIT
|
|
gptkbp:field
|
gptkb:artificial_intelligence
gptkb:machine_learning
deep learning
|
|
gptkbp:knownFor
|
hardware acceleration for AI
model pruning
efficient neural networks
deep learning model compression
|
|
gptkbp:nationality
|
gptkb:Chinese
|
|
gptkbp:notableWork
|
gptkb:TinyML
Deep Compression
EIE: Efficient Inference Engine
MCUNet
Once-for-All Network
|
|
gptkbp:occupation
|
gptkb:professor
|
|
gptkbp:position
|
Associate Professor
|
|
gptkbp:website
|
https://songhan.mit.edu/
|
|
gptkbp:bfsParent
|
gptkb:Kurt_Keutzer
|
|
gptkbp:bfsLayer
|
7
|
|
http://www.w3.org/2000/01/rdf-schema#label
|
Song Han
|