.png){kind=icon}
Return
Methods for Pruning Deep Neural Networks
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2022.3182659.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
This paper presents a survey of methods for pruning deep neural networks. It begins by categorising over 150 studies based on the underlying approach used and then focuses on three categories: methods that use magnitude based pruning, methods that utilise clustering to identify redundancy, and methods that use sensitivity analysis to assess the effect of pruning. Some of the key influencing studies within these categories are presented to highlight the underlying approaches and results achieved. Most studies present results which are distributed in the literature as new architectures, algorithms and data sets have developed with time, making comparison across different studied difficult. The paper therefore provides a resource for the community that can be used to quickly compare the results from many different methods on a variety of data sets, and a range of architectures, including AlexNet, ResNet, DenseNet and VGG. The resource is illustrated by comparing the results published for pruning AlexNet and ResNet50 on ImageNet and ResNet56 and VGG16 on the CIFAR10 data to reveal which pruning methods work well in terms of retaining accuracy whilst achieving good compression rates. The paper concludes by identifying some research gaps and promising directions for future research.
Keywords:
Deep learning
Neural networks
Computer architecture
Prediction algorithms
Weight measurement
Sensitivity analysis
Quantization (signal)
Deep learning
neural networks
pruning deep networks
Journal
IF:
3.6
Papers:
9.8W
Citations:
29.4W
Organization
Cited Papers
Degradation of reactive dyes I. A comparative study of ozonation, enzymatic and photochemical processes.png)
Chemosphere
ChemosphereIF0
PREAI
ShareSaveShareSaveShareSaveA Hierarchical Cardiac Rhythm Classification Methodology Based on Electrocardiogram Fiducial Points
OAAI
OAAIShareSaveShareSaveShareSave
View more