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

Backpropagation and the brain

Lillicrap, Timothy P.*; Santoro, Adam; Marris, Luke; Akerman, Colin J.; Hinton, Geoffrey*
Nature Reviews Neuroscience2020-6DOI: 10.1038/s41583-020-0277-3
405被引3阅读
引用收藏
分享

摘要

During learning, the brain modifies synapses to improve behaviour. In the cortex, synapses are embedded within multilayered networks, making it difficult to determine the effect of an individual synaptic modification on the behaviour of the system. The backpropagation algorithm solves this problem in deep artificial neural networks, but historically it has been viewed as biologically problematic. Nonetheless, recent developments in neuroscience and the successes of artificial neural networks have reinvigorated interest in whether backpropagation offers insights for understanding learning in the cortex. The backpropagation algorithm learns quickly by computing synaptic updates using feedback connections to deliver error signals. Although feedback connections are ubiquitous in the cortex, it is difficult to see how they could deliver the error signals required by strict formulations of backpropagation. Here we build on past and recent developments to argue that feedback connections may instead induce neural activities whose differences can be used to locally approximate these signals and hence drive effective learning in deep networks in the brain. The backpropagation of error (backprop) algorithm is frequently used to train deep neural networks in machine learning, but it has not been viewed as being implemented by the brain. In this Perspective, however, Lillicrap and colleagues argue that the key principles underlying backprop may indeed have a role in brain function.

学科与关键词

关键词
LONG-LASTING POTENTIATIONVISUAL CORTICAL AREASDEEP NEURAL-NETWORKSSYNAPTIC PLASTICITYSELECTIVE ATTENTIONSINGLE NEURONSLEARNING RULECORTEXCELLV4
相关
加载中…
  • 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
  • If deep learning is the answer, what is the question?
    Saxe, Andrew*; Nelli, Stephanie*; Summerfield, Christopher*Nature Reviews Neuroscience, 2021, 22(1): 55-67.被引 160
  • Neuroevolution gives rise to more focused information transfer compared to backpropagation in recurrent neural networks
    Hintze, Arend*; Adami, ChristophNEURAL COMPUTING & APPLICATIONS, 2022.被引 2
查看全部 →

发表信息

论文状态
公开发表
期刊
Nature Reviews Neuroscience
发表日期
2020-06
卷期
第 21 卷, 第 6 期
页码
335-346
DOI
10.1038/s41583-020-0277-3
语言
ENGLISH
期刊收录
NSL.SCIE
期刊等级
1区
成果收录
SCIE
资助标注
BBSRC [BB/S007938/1] Funding Source: UKRI

作者

  • L

    Lillicrap, Timothy P. (通讯) (第一作者)

  • S

    Santoro, Adam

查看全部 5 位作者收起作者
  • M

    Marris, Luke

  • A

    Akerman, Colin J.

  • H

    Hinton, Geoffrey (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