A Cost-Efficient Approximate Dynamic Ranged Multiplication and Approximation-Aware Training on Convolutional Neural Networks

This paper proposes a low-cost approximate dynamic ranged multiplier and describes its use during the training process on convolutional neural networks (CNNs). It has been noted that the approximate multiplier can be used in the convolution of CNN’s forward path. However, in CNN inference on...

Deskribapen osoa

Xehetasun bibliografikoak

Egile Nagusiak:	Hyunjin Kim, Alberto A. Del Barrio
Formatua:	Artigo
Hizkuntza:	Inglês
Argitaratua:	IEEE 2021-01-01
Saila:	IEEE Access
Gaiak:	Approximate computing approximate multiplier approximation-aware training convolutional neural network probabilistic multiplier
Sarrera elektronikoa:	https://ieeexplore.ieee.org/document/9555631/
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!