An Approach to Pruning the Structure of Convolutional Neural Networks without Loss of Generalization Ability

期刊论文
发表日期：

2024年6月1日

查看全文

Chaoxiang Chen,
Aliaksandr Kroshchanka,
Vladimir Golovko,
Olha Golovko

摘要

Abstract

This paper proposes an approach to pruning the parameters of convolutional neural networks using unsupervised pretraining. The authors demonstrate that the proposed approach makes it possible to reduce the number of configurable parameters of a convolutional neural network without loss of generalization ability. A comparison of the proposed approach and existing pruning techniques is made. The capabilities of the proposed algorithm are demonstrated on classical CIFAR10 and CIFAR100 computer vision samples.