Results 21 to 30 of about 36,322 (258)
Sensors, 2021 Deep neural networks have achieved significant development and wide applications for their amazing performance. However, their complex structure, high computation and storage resource limit their applications in mobile or embedding devices such as sensor
Tao Wu +4 more
doaj +1 more source
Roulette: A Pruning Framework to Train a Sparse Neural Network From Scratch
IEEE Access, 2021 Due to space and inference time restrictions, finding an efficient and sparse sub-network from a dense and over-parameterized network is critical for deploying neural networks on edge devices.
Qiaoling Zhong +3 more
doaj +1 more source
CoRR, 2022 Deep learning models that perform well often have high computational costs. In this paper, we combine two approaches that try to reduce the computational cost while keeping the model performance high: pruning and early exit networks. We evaluate two approaches of pruning early exit networks: (1) pruning the entire network at once, (2) pruning the base ...
Alperen Görmez, Erdem Koyuncu
openaire +2 more sources
Mathematics, 2023 Among various network compression methods, network pruning has developed rapidly due to its superior compression performance. However, the trivial pruning threshold limits the compression performance of pruning.
Yunlong Ding, Di-Rong Chen
doaj +1 more source
Differentiable Network Pruning for Microcontrollers
CoRR, 2021 Embedded and personal IoT devices are powered by microcontroller units (MCUs), whose extreme resource scarcity is a major obstacle for applications relying on on-device deep learning inference. Orders of magnitude less storage, memory and computational capacity, compared to what is typically required to execute neural networks, impose strict structural
Liberis, Edgar, Lane, Nicholas D.
openaire +2 more sources
Slimmable Pruned Neural Networks
CoRR, 2022 Slimmable Neural Networks (S-Net) is a novel network which enabled to select one of the predefined proportions of channels (sub-network) dynamically depending on the current computational resource availability. The accuracy of each sub-network on S-Net, however, is inferior to that of individually trained networks of the same size due to its difficulty
Hideaki Kuratsu, Atsuyoshi Nakamura
openaire +2 more sources
Heuristic Method for Minimizing Model Size of CNN by Combining Multiple Pruning Techniques
Sensors, 2022 Network pruning techniques have been widely used for compressing computational and memory intensive deep learning models through removing redundant components of the model.
Danhe Tian +2 more
doaj +1 more source
Methods for Pruning Deep Neural Networks [PDF]
IEEE Access, 2022 Major revision that includes additional references and a new section for comparison of ...
Sunil Vadera, Salem Ameen
openaire +3 more sources
Remote Sensing, 2023 The rapid development of neural networks has come at the cost of increased computational complexity. Neural networks are both computationally intensive and memory intensive; as such, the minimal energy and computing power of satellites pose a challenge ...
Penghao Xiao +4 more
doaj +1 more source
A Verification Method on Post-Pruning Generalization Ability of Neural Network Model [PDF]
Jisuanji gongcheng, 2019 To address the over-fitting problem caused by the down-regulation of the Dropout rate in the pruning operation of the neural network model,a verification method for the generalization ability of the pruning model is proposed.By artificially occluding the
LIU Chongyang, LIU Qinrang
doaj +1 more source