Robust 2-bit Quantization of Weights in Neural Network Modeled by Laplacian Distribution

Robust 2-bit Quantization of Weights in Neural Network Modeled by Laplacian Distribution

Significant efforts are constantly involved in finding manners to decrease the number of bits required for quantization of neural network parameters. Although in addition to compression, in neural networks, the application of quantizer models that are robust to changes in the variance of input dat...

Full description

Bibliographic Details
Main Authors: PERIC, Z., DENIC, B., DINCIC, M., NIKOLIC, J.
Format: Article
Language:English
Published: Stefan cel Mare University of Suceava 2021-08-01
Series:Advances in Electrical and Computer Engineering
Subjects:
image classification
neural networks
quantization
signal to noise ratio
source coding
Online Access:http://dx.doi.org/10.4316/AECE.2021.03001

Internet

http://dx.doi.org/10.4316/AECE.2021.03001

Similar Items