Toward accurate binarized neural networks with sparsity for mobile application

P Wang, X He, J Cheng - IEEE Transactions on Neural …, 2022 - ieeexplore.ieee.org
While binarized neural networks (BNNs) have attracted great interest, popular approaches
proposed so far mainly exploit the symmetric function for feature binarization, ie, to binarize …

OvSW: Overcoming Silent Weights for Accurate Binary Neural Networks

J Xiang, Z Chen, S Li, Q Wu, Y Liu - European Conference on Computer …, 2025 - Springer
Abstract Binary Neural Networks (BNNs) have been proven to be highly effective for
deploying deep neural networks on mobile and embedded platforms. Most existing works …

[PDF][PDF] Improving Gradient Paths for Binary Convolutional Neural Networks.

B Zhu, HP Hofstee, J Lee, Z Al-Ars - BMVC, 2022 - bmvc2022.mpi-inf.mpg.de
Our starting point is a closer investigation of Bi-Real ResNet [34]. In our investigation of Bi-
Real ResNet, we believe that the superiority of Bi-Real ResNet over binary ResNet requires …

How to train accurate BNNs for embedded systems?

FAM Putter, H Corporaal - … Machine Learning for Cyber-Physical, IoT, and …, 2023 - Springer
A key enabler of deploying convolutional neural networks on resource-constrained
embedded systems is the binary neural network (BNN). BNNs save on memory and simplify …

SGDAT: An optimization method for binary neural networks

G Shan, Z Guoyin, J Chengwei, W Yanxia - Neurocomputing, 2023 - Elsevier
Stochastic gradient descent (SGD), one of the most popular neural network optimization
algorithms, has a solid theoretical foundation as well as good generalization performance …