IKW: Inter-Kernel Weights for Power Efficient Edge Computing

IKW: Inter-Kernel Weights for Power Efficient Edge Computing

Deep Convolutional Neural Networks (CNN) have achieved state-of-the-art recognition accuracy in a wide range of computer vision applications like image classification, object detection, semantic segmentation etc. Applications based on CNN require millions of multiply-accumulate (MAC) operations to b...

Full description

Bibliographic Details
Main Authors: Pramod Udupa, Gopinath Mahale, Kiran Kolar Chandrasekharan, Sehwan Lee
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Inter-kernel weights
quantization
multiply-accumulate unit
split accumulator
kernel zero skipping
convolutional neural network
Online Access:https://ieeexplore.ieee.org/document/9090142/

Internet

https://ieeexplore.ieee.org/document/9090142/

Similar Items