Results 41 to 50 of about 36,322 (258)
Applied Sciences, 2022 The superior performance of the recent deep learning models comes at the cost of a significant increase in computational complexity, memory use, and power consumption.
Deepak Ghimire, Seong-Heum Kim
doaj +1 more source
Double Standard Pruning of Convolution Network Based on Feature Extraction of Intermediate Graph [PDF]
Jisuanji gongcheng, 2023 Convolutional Neural Network(CNN) require a considerable amount of overhead in terms of computation and storage.To deploy and run a CNN on embedded devices with a poor computing power and storage capacity, this study proposes a convolution kernel double ...
CHENG Xiaohui, LI Yu, KANG Yanping
doaj +1 more source
Dissecting Pruned Neural Networks
CoRR, 2019 Pruning is a standard technique for removing unnecessary structure from a neural network to reduce its storage footprint, computational demands, or energy consumption. Pruning can reduce the parameter-counts of many state-of-the-art neural networks by an order of magnitude without compromising accuracy, meaning these networks contain a vast amount of ...
Jonathan Frankle, David Bau
openaire +2 more sources
Efficient Digital Predistortion Using Sparse Neural Network
IEEE Access, 2020 This paper proposes an efficient neural-network-based digital predistortion (DPD), named as envelope time-delay neural network (ETDNN) DPD. The method complies with the physical characteristics of radio-frequency (RF) power amplifiers (PAs) and uses a ...
Masaaki Tanio +2 more
doaj +1 more source
Self-Adaptive Network Pruning [PDF]
, 2019 Deep convolutional neural networks have been proved successful on a wide range of tasks, yet they are still hindered by their large computation cost in many industrial scenarios. In this paper, we propose to reduce such cost for CNNs through a self-adaptive network pruning method (SANP). Our method introduces a general Saliency-and-Pruning Module (SPM)
Jinting Chen +3 more
openaire +2 more sources
Remote Sensing, 2023 Neural network models for hyperspectral images classification are complex and therefore difficult to deploy directly onto mobile platforms. Neural network model compression methods can effectively optimize the storage space and inference time of the ...
Yu Lei +5 more
doaj +1 more source
A "Network Pruning Network" Approach to Deep Model Compression [PDF]
2020 IEEE Winter Conference on Applications of Computer Vision (WACV), 2020 Accepted in WACV ...
Vinay Kumar Verma +3 more
openaire +2 more sources
Activation-Based Pruning of Neural Networks
AlgorithmsWe present a novel technique for pruning called activation-based pruning to effectively prune fully connected feedforward neural networks for multi-object classification. Our technique is based on the number of times each neuron is activated during model
Tushar Ganguli, Edwin K. P. Chong
doaj +1 more source
IEEE Access, 2020 The enormous inference cost of deep neural networks can be mitigated by network compression. Pruning connections is one of the predominant approaches used for network compression.
Sai Aparna Aketi +3 more
doaj +1 more source
Providing clear pruning threshold: A novel CNN pruning method via L0 regularisation
IET Image Processing, 2021 Network pruning is a significant way to improve the practicability of convolution neural networks (CNNs) by removing the redundant structure of the network model. However, in most of the existing network pruning methods l1 or l2 regularisation is applied
Guo Li, Gang Xu
doaj +1 more source