DDMI: a model information evaluation method based on deep dream

IF 6.3 2区计算机科学 Q1 TELECOMMUNICATIONS

Digital Communications and Networks Pub Date : 2026-03-01 Epub Date: 2025-03-17 DOI:10.1016/j.dcan.2025.03.008

Yana Yang , Haoyu Li , Shuai Xiao , Guipeng Lan , Yong Zhu , Ziqiang Huo

{"title":"DDMI: a model information evaluation method based on deep dream","authors":"Yana Yang , Haoyu Li , Shuai Xiao , Guipeng Lan , Yong Zhu , Ziqiang Huo","doi":"10.1016/j.dcan.2025.03.008","DOIUrl":null,"url":null,"abstract":"<div><div>In recent years, the Internet of Everything (IoE) has been developing rapidly; however, there are currently issues with efficiency and sustainability within IoE. To address this problem, model lightweighting can be employed by constraining the size of deep learning models, thereby reducing the demand for computational resources and ensuring the efficiency and sustainability of IoE devices. In this regard, we propose a model information evaluation method based on DeepDream. This method does not require real samples to participate; instead, it evaluates the importance of each neuron based on the model's own information. Additionally, we introduce a method for automatically selecting high-information neurons, which can identify neurons that have a significant impact on the model. We also present a visualization method for neuron class information, which can visualize information related to various classes within neurons. Through experiments, we demonstrate the effectiveness of the methods we have proposed.</div></div>","PeriodicalId":48631,"journal":{"name":"Digital Communications and Networks","volume":"12 3","pages":"Pages 530-539"},"PeriodicalIF":6.3000,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Digital Communications and Networks","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2352864825000331","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/3/17 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"TELECOMMUNICATIONS","Score":null,"Total":0}

引用次数: 0

Abstract

In recent years, the Internet of Everything (IoE) has been developing rapidly; however, there are currently issues with efficiency and sustainability within IoE. To address this problem, model lightweighting can be employed by constraining the size of deep learning models, thereby reducing the demand for computational resources and ensuring the efficiency and sustainability of IoE devices. In this regard, we propose a model information evaluation method based on DeepDream. This method does not require real samples to participate; instead, it evaluates the importance of each neuron based on the model's own information. Additionally, we introduce a method for automatically selecting high-information neurons, which can identify neurons that have a significant impact on the model. We also present a visualization method for neuron class information, which can visualize information related to various classes within neurons. Through experiments, we demonstrate the effectiveness of the methods we have proposed.

查看原文本刊更多论文

DDMI：一种基于深度梦的模型信息评价方法

近年来，万物互联（IoE）发展迅速；然而，目前在物联网的效率和可持续性方面存在问题。为了解决这个问题，可以通过限制深度学习模型的大小来实现模型轻量化，从而减少对计算资源的需求，确保物联网设备的效率和可持续性。为此，我们提出了一种基于DeepDream的模型信息评价方法。该方法不需要真实样本参与；相反，它根据模型自身的信息来评估每个神经元的重要性。此外，我们引入了一种自动选择高信息神经元的方法，该方法可以识别对模型有重大影响的神经元。我们还提出了一种神经元类信息的可视化方法，该方法可以可视化神经元中与各种类别相关的信息。通过实验，我们证明了我们所提出的方法的有效性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Digital Communications and Networks Computer Science-Hardware and Architecture

CiteScore

12.80

自引率

5.10%

发文量

915

审稿时长

30 weeks

期刊介绍： Digital Communications and Networks is a prestigious journal that emphasizes on communication systems and networks. We publish only top-notch original articles and authoritative reviews, which undergo rigorous peer-review. We are proud to announce that all our articles are fully Open Access and can be accessed on ScienceDirect. Our journal is recognized and indexed by eminent databases such as the Science Citation Index Expanded (SCIE) and Scopus. In addition to regular articles, we may also consider exceptional conference papers that have been significantly expanded. Furthermore, we periodically release special issues that focus on specific aspects of the field. In conclusion, Digital Communications and Networks is a leading journal that guarantees exceptional quality and accessibility for researchers and scholars in the field of communication systems and networks.