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

Learning Invariance from Natural Images Inspired by Observations in the Primary Visual Cortex

Teichmann, Michael*; Wiltschut, Jan; Hamker, Fred
Neural Computation2012-5DOI: 10.1162/NECO_a_00268
7被引11阅读
引用收藏
分享

摘要

The human visual system has the remarkable ability to largely recognize objects invariant of their position, rotation, and scale. A good interpretation of neurobiological findings involves a computational model that simulates signal processing of the visual cortex. In part, this is likely achieved step by step from early to late areas of visual perception. While several algorithms have been proposed for learning feature detectors, only few studies at hand cover the issue of biologically plausible learning of such invariance. In this study, a set of Hebbian learning rules based on calcium dynamics and homeostatic regulations of single neurons is proposed. Their performance is verified within a simple model of the primary visual cortex to learn so-called complex cells, based on a sequence of static images. As a result, the learned complex-cell responses are largely invariant to phase and position.

学科与关键词

关键词
BIDIRECTIONAL SYNAPTIC PLASTICITYCOMPLEX CELL PROPERTIESSLOW FEATURE ANALYSISRECEPTIVE-FIELDSOBJECT RECOGNITIONINDEPENDENT COMPONENTSBINOCULAR INTERACTIONGENERATIVE MODELACTIVE NEURONSNETWORK LEARNS
相关
加载中…
  • Neurons with two sites of synaptic integration learn invariant representations
    Krding, KP; Knig, PNeural Computation, 2001, 13(12): 2823-2849.被引 15
  • Unsupervised learning by competing hidden units
    Krotov, Dmitry*; Hopfield, John J.*PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2019, 116(16): 7723-7731.被引 81
  • Visual channels, Hebbian assemblies and the effect of Hebb's rule
    Mortensen, U; Nachtigall, CBiological Cybernetics, 2000, 82(5): 401-413.被引 5
查看全部 →

发表信息

论文状态
公开发表
期刊
Neural Computation
发表日期
2012-05
卷期
第 24 卷, 第 5 期
页码
1271-1296
DOI
10.1162/NECO_a_00268
语言
ENGLISH
成果收录
SCIE
资助标注
German Science Foundation (DFG) [HA2630/6-1]

作者

  • T

    Teichmann, Michael (通讯) (第一作者)

  • W

    Wiltschut, Jan

查看全部 3 位作者收起作者
  • H

    Hamker, Fred

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