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

Pyramidal Predictive Network: A Model for Visual-Frame Prediction Based on Predictive Coding Theory

Ling, Chaofan; Zhong, Junpei*; Li, Weihua*hong kong polytech univ
Electronics2022-9DOI: 10.3390/electronics11182969
1被引12阅读
引用收藏
分享

摘要

Visual-frame prediction is a pixel-dense prediction task that infers future frames from past frames. A lack of appearance details, low prediction accuracy and a high computational overhead are still major problems associated with current models or methods. In this paper, we propose a novel neural network model inspired by the well-known predictive coding theory to deal with these problems. Predictive coding provides an interesting and reliable computational framework. We combined this approach with other theories, such as the theory that the cerebral cortex oscillates at different frequencies at different levels, to design an efficient and reliable predictive network model for visual-frame prediction. Specifically, the model is composed of a series of recurrent and convolutional units forming the top-down and bottom-up streams, respectively. The update frequency of neural units on each of the layers decreases with the increase in the network level, which means that neurons of a higher level can capture information in longer time dimensions. According to the experimental results, this model showed better compactness and comparable predictive performance with those of existing works, implying lower computational cost and higher prediction accuracy.

学科与关键词

关键词
predictive codingvideo predictionneural network
相关
加载中…
  • Predictive Coding, Variational Autoencoders, and Biological Connections
    Marino, Joseph*Neural Computation, 2021, 34(1): 1-44.被引 22
  • Predictive Coding Approximates Backprop Along Arbitrary Computation Graphs
    Millidge, Beren*; Tschantz, Alexander; Buckley, Christopher L.Neural Computation, 2022, 34(6): 1329-1368.被引 18
  • Cortical and subcortical predictive dynamics and learning during perception, cognition, emotion and action
    Grossberg, Stephen*Philosophical Transactions of the Royal Society B: Biological Sciences , 2009, 364(1521): 1223-1234.被引 62
查看全部 →

发表信息

论文状态
公开发表
期刊
Electronics
发表日期
2022-09
卷期
第 11 卷, 第 18 期
页码
2969
DOI
10.3390/electronics11182969
期刊等级
4区
成果收录
SCIE
资助标注
Key-Area Research and Development Program of Guangdong Province [2019B090912001]; PolyU Grants [ZVUY-P0035417, CD5EP0043422, WZ09-P0043123]

作者

  • L

    Ling, Chaofan (第一作者)

  • Z

    Zhong, Junpei (通讯)

    hong kong polytech univ

查看全部 3 位作者收起作者
  • L

    Li, Weihua (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