Results 51 to 60 of about 79,498 (272)

Fine-Pruning: Joint Fine-Tuning and Compression of a Convolutional Network with Bayesian Optimization

, 2017
When approaching a novel visual recognition problem in a specialized image domain, a common strategy is to start with a pre-trained deep neural network and fine-tune it to the specialized domain.
Mori, Greg, Muralidharan, Srikanth, Tung, Frederick   +2 more
core   +1 more source

Spectral Pruning for Recurrent Neural Networks

CoRR, 2021
Recurrent neural networks (RNNs) are a class of neural networks used in sequential tasks. However, in general, RNNs have a large number of parameters and involve enormous computational costs by repeating the recurrent structures in many time steps. As a method to overcome this difficulty, RNN pruning has attracted increasing attention in recent years ...
Takashi Furuya, Kazuma Suetake, Koichi Taniguchi, Hiroyuki Kusumoto, Ryuji Saiin, Tomohiro Daimon   +5 more
openaire   +3 more sources

Lossless Reconstruction of Convolutional Neural Network for Channel-Based Network Pruning

Sensors, 2023
Network pruning reduces the number of parameters and computational costs of convolutional neural networks while maintaining high performance. Although existing pruning methods have achieved excellent results, they do not consider reconstruction after ...
Donghyeon Lee, Eunho Lee, Youngbae Hwang
doaj   +1 more source

Directional Pruning of Deep Neural Networks

CoRR, 2020
In the light of the fact that the stochastic gradient descent (SGD) often finds a flat minimum valley in the training loss, we propose a novel directional pruning method which searches for a sparse minimizer in or close to that flat region. The proposed pruning method does not require retraining or the expert knowledge on the sparsity level.
Shih-Kang Chao, Zhanyu Wang, Yue Xing 0002, Guang Cheng 0003   +3 more
openaire   +3 more sources

Automated Pruning for Deep Neural Network Compression

, 2019
In this work we present a method to improve the pruning step of the current state-of-the-art methodology to compress neural networks. The novelty of the proposed pruning technique is in its differentiability, which allows pruning to be performed during ...
Bianco, Simone, Manessi, Franco, Napoletano, Paolo, Rozza, Alessandro, Schettini, Raimondo   +4 more
core   +1 more source

Demystifying Neural Network Filter Pruning

CoRR, 2018
Based on filter magnitude ranking (e.g. L1 norm), conventional filter pruning methods for Convolutional Neural Networks (CNNs) have been proved with great effectiveness in computation load reduction. Although effective, these methods are rarely analyzed in a perspective of filter functionality.
Zhuwei Qin, Fuxun Yu, Chenchen Liu, Xiang Chen 0010   +3 more
openaire   +2 more sources

Diffusion Spectrum Imaging Maps Early Axonal Loss and a Unique Progressive Signal in Neuronal Intranuclear Inclusion Disease

Annals of Clinical and Translational Neurology, EarlyView.
ABSTRACT Objective To delineate specific in vivo white matter pathology in neuronal intranuclear inclusion disease (NIID) using diffusion spectrum imaging (DSI) and define its clinical relevance. Methods DSI was performed on 42 NIID patients and 38 matched controls.
Kaiyan Jiang, Yixiu Pei, Xiaobao Hu, Ying Xiong, Fang Wang, Yanyan Yu, Min Zhu, Dandan Tan, Meihong Zhou, Daojun Hong, Fuqing Zhou   +10 more
wiley   +1 more source

Quantization Robust Pruning With Knowledge Distillation

IEEE Access, 2023
To resolve the problem that deep neural networks (DNN) require a large number of network parameters, many researchers have sought to compress the network.
Jangho Kim
doaj   +1 more source

Multifunctional Bio‐Based Packaging for Perishable Foods: Structural Design, Scalable Fabrication, and Versatile Applications

Advanced Materials, EarlyView.
An overview of design principles and scalable fabrication strategies for multifunctional bio‐based packaging. Radiative cooling films, modified‐atmosphere films/membranes, active antimicrobial/antioxidant platforms, intelligent optical/electrochemical labels, and superhydrophobic surfaces are co‐engineered from material chemistry to mesoscale structure
Lei Zhang, Jiaqi Zhang, Mei Cui, Wei Qi, Renliang Huang, Rongxin Su, Kai Zhang   +6 more
wiley   +1 more source

Intelligent Fault Diagnosis Method for Blade Damage of Quad-Rotor UAV Based on Stacked Pruning Sparse Denoising Autoencoder and Convolutional Neural Network

Machines, 2021
This paper introduces a new intelligent fault diagnosis method based on stack pruning sparse denoising autoencoder and convolutional neural network (sPSDAE-CNN).
Pu Yang, Chenwan Wen, Huilin Geng, Peng Liu   +3 more
doaj   +1 more source