ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Deep learning systems as complex networks

Testolin, Alberto; Piccolini, Michele; Suweis, Samir*
Journal of Complex Networks2020-2DOI: 10.1093/comnet/cnz018
14被引6阅读
引用收藏
分享

摘要

Thanks to the availability of large scale digital datasets and massive amounts of computational power, deep learning algorithms can learn representations of data by exploiting multiple levels of abstraction. These machine-learning methods have greatly improved the state-of-the-art in many challenging cognitive tasks, such as visual object recognition, speech processing, natural language understanding and automatic translation. In particular, one class of deep learning models, known as deep belief networks (DBNs), can discover intricate statistical structure in large datasets in a completely unsupervised fashion, by learning a generative model of the data using Hebbian-like learning mechanisms. Although these self-organizing systems can be conveniently formalized within the framework of statistical mechanics, their internal functioning remains opaque, because their emergent dynamics cannot be solved analytically. In this article, we propose to study DBNs using techniques commonly employed in the study of complex networks, in order to gain some insights into the structural and functional properties of the computational graph resulting from the learning process.

学科与关键词

关键词
networks theoryartificial neural networksdeep belief networkshierarchical generative modelsmachine learninggraph analysis
相关
加载中…

文献加载失败,请重试

重试

发表信息

论文状态
公开发表
期刊
Journal of Complex Networks
发表日期
2020-02
卷期
第 8 卷, 第 1 期
页码
cnz018
DOI
10.1093/comnet/cnz018
期刊收录
SCIE
成果收录
SCIE
资助标注
University of Padova

作者

  • T

    Testolin, Alberto (第一作者)

  • P

    Piccolini, Michele

查看全部 3 位作者收起作者
  • S

    Suweis, Samir (通讯)

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417