Results 211 to 220 of about 14,609 (251)

A lightweight network for phone surface defect detection with industrial deployment on RK3568 edge devices. [PDF]

PLoS One
Zhuo S, Zhou X, Cai J, Bai H, Duan X, Ma Y.   +5 more
europepmc   +1 more source

Comprehensive Chemical and Biological Evaluation of <i>Rosa damascena</i> Plant Parts and Industrial Residues Using FTIR-ATR and LC-MS/MS. [PDF]

Food Sci Nutr
Bayrak B, Yuca H, Budak YB, Alkuyruk SB, Özer EB, Bona GE, Aydın B, Karadayı M, Gülşahin Y, Atila A, Göger G, Karakaya S.   +11 more
europepmc   +1 more source

Computational Quantification of Mouse Retinal Vasculature Using ImageJ.

Bio Protoc
Nader M, Feridooni HA, Tavasoli M, Van Der Ende S, McMaster CR, Robitaille JM.   +5 more
europepmc   +1 more source

Some of the next articles are maybe not open access.

Related searches:

Filter Pruning via Automatic Pruning Rate Search

Lecture Notes in Computer Science, 2023
Shan Cao, Zhixiang Chen, Cao Shan
exaly   +2 more sources

Adaptive Filter Pruning via Sensitivity Feedback

IEEE Transactions on Neural Networks and Learning Systems
Filter pruning is advocated for accelerating deep neural networks without dedicated hardware or libraries, while maintaining high prediction accuracy. Several works have cast pruning as a variant of l1 -regularized training, which entails two challenges: 1) the l1 -norm is not scaling-invariant (i.e., the regularization penalty depends on weight values)
Nikolaos M Fréris, Yuyao Zhang
exaly   +3 more sources

Filter pruning - deeper layers need fewer filters

Journal of Intelligent & Fuzzy Systems, 2022
Model pruning aims to reduce the parameter amount of deep neural networks while retaining the performance. Existing strategies often treat all layers equally and all layers simply share the same pruning rate. However, it is observed from our experiments that the redundancy degree differs from layer to layer.
Heng Wang, Xiang Ye, Yong Li 0025
openaire   +1 more source

Soft independence guided filter pruning

Pattern Recognition
Chenyang Shen, Qinghua Hu, Liu Yang
exaly   +2 more sources

Filter Pruning Based on Connection Sensitivity

Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems, 2020
For the goal of reducing the remarkable redundancy in deep convolutional neural networks (CNNs), we propose an efficient framework to compress and accelerate CNN models. This work focus on pruning at filter level, mainly removing those less important filters.
Yinong Xu, Yunsen Liao, Ying Zhao
openaire   +2 more sources

On the performance of adaptive pruned Volterra filters

Signal Processing, 2013
Because of the high computational burden required by adaptive Volterra filters, several of their practical implementations consider some type of sparseness for complexity reduction. Such implementations are obtained using application-oriented strategies to prune a standard Volterra filter by zeroing some of its coefficients.
Eduardo Luiz Ortiz Batista, Rui Seara
openaire   +1 more source

Considering Filter Importance and Irreplaceability In Filter Pruning

2021 International Conference on Computer Communication and Artificial Intelligence (CCAI), 2021
Deep convolutional neural network (CNNs) have gained a great success in computer vision tasks. However, the computation and parameter storage costs of CNNs are very large, thus a large number of studies have tried to reduce the computation and parameters of CNNs. Quantization and pruning are the usual strategies for model compression.
openaire   +1 more source