STPCNN: Selection of transfer parameters in convolutional neural networks

Author:

Mallouk Otmane1ORCID,Joudar Nour‐Eddine1,Ettaouil Mohamed1

Affiliation:

1. Faculty of Science and Technology of Fez, Department of Mathematics, Modelling and Mathematical Structures Laboratory Sidi Mohamed Ben Abdellah University Fez Morocco

Abstract

AbstractNowadays, transfer learning has shown promising results in many applications. However, most deep transfer learning methods such as parameter sharing and fine‐tuning are still suffering from the lack of parameters transmission strategy. In this paper, we propose a new optimization model for parameter‐based transfer learning in convolutional neural networks named STP‐CNN. Indeed, we propose a Lasso transfer model supported by a regularization term that controls transferability. Moreover, we opt for the proximal gradient descent method to solve the proposed model. The suggested technique allows, under certain conditions, to control exactly which parameters, in each convolutional layer of the source network, which will be used directly or adjusted in the target network. Several experiments prove the performance of our model in locating the transferable parameters as well as improving the data classification.

Publisher

Wiley

Reference42 articles.

1. Ajakan H. Germain P. Larochelle H. Laviolette F. &Marchand M.(2014).Domain‐adversarial neural networks.arXiv preprint arXiv:1412.4446.

2. Asgarian A. Sobhani P. Zhang J. C. Mihailescu M. Sibilia A. Ashraf A. B. &Taati B.(2018).A hybrid instance‐based transfer learning method.arXiv preprint arXiv:1812.01063.

3. Unsupervised Transfer Learning via Multi-Scale Convolutional Sparse Coding for Biomedical Applications

4. ImageNet: A large-scale hierarchical image database

5. Duan J. Dasgupta A. Fischer J. &Tan C.(2022).A survey on machine learning approaches for modelling intuitive physics.arXiv preprint arXiv:2202.06481.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3