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

Predictive Coding Approximates Backprop Along Arbitrary Computation Graphs

Millidge, Beren*; Tschantz, Alexander; Buckley, Christopher L.
Neural Computation2022-5-19DOI: 10.1162/neco_a_01497
18被引1阅读
引用收藏
分享

摘要

Backpropagation of error (backprop) is a powerful algorithm for training machine learning architectures through end-to-end differentiation. Recently it has been shown that backprop in multilayer perceptrons (MLPs) can be approximated using predictive coding, a biologically plausible process theory of cortical computation that relies solely on local and Hebbian updates. The power of backprop, however, lies not in its instantiation in MLPs but in the concept of automatic differentiation, which allows for the optimization of any differentiable program expressed as a computation graph. Here, we demonstrate that predictive coding converges asymptotically (and in practice, rapidly) to exact backprop gradients on arbitrary computation graphs using only local learning rules. We apply this result to develop a straightforward strategy to translate core machine learning architectures into their predictive coding equivalents. We construct predictive coding convolutional neural networks, recurrent neural networks, and the more complex long short-term memory, which include a nonlayer-like branching internal graph structure and multiplicative interactions. Our models perform equivalently to backprop on challenging machine learning benchmarks while using only local and (mostly) Hebbian plasticity. Our method raises the potential that standard machine learning algorithms could in principle be directly implemented in neural circuitry and may also contribute to the development of completely distributed neuromorphic architectures.

学科与关键词

关键词
NEURAL-NETWORKSFREE-ENERGYREINFORCEMENTINFERENCEALGORITHMLEVEL
相关
加载中…
  • Backpropagation and the brain
    Lillicrap, Timothy P.*; Santoro, Adam; Marris, Luke; Akerman, Colin J.; Hinton, Geoffrey*Nature Reviews Neuroscience, 2020, 21(6): 335-346.被引 405
  • Predictive Coding, Variational Autoencoders, and Biological Connections
    Marino, Joseph*Neural Computation, 2021, 34(1): 1-44.被引 22
  • Learning probability distributions of sensory inputs with Monte Carlo predictive coding
    Oliviers, Gaspard*; Bogacz, Rafal; Meulemans, AlexanderPLoS Computational Biology, 2024, 20(10): e1012532.
查看全部 →

发表信息

论文状态
公开发表
期刊
Neural Computation
发表日期
2022-05-19
卷期
第 34 卷, 第 6 期
页码
1329-1368
DOI
10.1162/neco_a_01497
语言
ENGLISH
期刊等级
4区
成果收录
SCIE
资助标注
EPSRC; Dr. Mortimer and Theresa Sackler Foundation; School of Engineering and Informatics at the University of Sussex; BBRSC [BB/P022197/1]; National Institutes of Natural Sciences, Japan [01112005]; BBSRC [BB/P022197/1] Funding Source: UKRI

作者

  • M

    Millidge, Beren (通讯) (第一作者)

  • T

    Tschantz, Alexander

查看全部 3 位作者收起作者
  • B

    Buckley, Christopher L.

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