Histogram-Equalized Quantization for logic-gated Residual Neural Networks

Adjusting the quantization according to the data or to the model loss seems mandatory to enable a high accuracy in the context of quantized neural networks. This work presents Histogram-Equalized Quantization (HEQ), an adaptive framework for linear and symmetric quantization. HEQ automatically adapt...

Full description

Saved in:
Bibliographic Details
Main Authors: Nguyen, Van Thien, Guicquero, William, Sicard, Gilles
Format: Conference Proceeding
Language:English
Subjects:
Adaptation models
CNN
Data models
Hardware
histogram equalization
Histograms
logic-gated CNN
Neural networks
Quantization (signal)
quantized neural networks
skip connections
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Adjusting the quantization according to the data or to the model loss seems mandatory to enable a high accuracy in the context of quantized neural networks. This work presents Histogram-Equalized Quantization (HEQ), an adaptive framework for linear and symmetric quantization. HEQ automatically adapts the quantization thresholds using a unique step size optimization. We empirically show that HEQ achieves state-of-the-art performances on CFAR-10. Experiments on the STL-10 dataset even show that HEQ enables a proper training of our proposed logic-gated (OR, MUX) residual networks with a higher accuracy at a lower hardware complexity than previous work.
ISSN:2158-1525
DOI:10.1109/ISCAS48785.2022.9937290