Toward accurate binarized neural networks with sparsity for mobile application
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 …
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 …
deploying deep neural networks on mobile and embedded platforms. Most existing works …
[PDF][PDF] Improving Gradient Paths for Binary Convolutional Neural Networks.
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 …
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 …
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 …
algorithms, has a solid theoretical foundation as well as good generalization performance …