ZeNA: Zero-Aware Neural Network Accelerator
Dongyoung Kim, Junwhan Ahn, Sungjoo Yoo · IEEE Design and Test · 2017
It has been observed that the majority of the kernel weights and input activations in the state-of-the-art convolution neural networks (CNNs) have zero values. This article proposes a CNN hardware accelerator that exploits this property to achieve significant performance and energy improvements.