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

A Gaussian Attractor Network for Memory and Recognition with Experience-Dependent Learning

Hu, Xiaolin*; Zhang, Bo清华大学
Neural Computation2010-5DOI: 10.1162/neco.2010.02-09-957
6被引13阅读
引用收藏
分享

摘要

Attractor networks are widely believed to underlie the memory systems of animals across different species. Existing models have succeeded in qualitatively modeling properties of attractor dynamics, but their computational abilities often suffer from poor representations for realistic complex patterns, spurious attractors, low storage capacity, and difficulty in identifying attractive fields of attractors. We propose a simple two-layer architecture, gaussian attractor network, which has no spurious attractors if patterns to be stored are uncorrelated and can store as many patterns as the number of neurons in the output layer. Meanwhile the attractive fields can be precisely quantified and manipulated. Equipped with experience-dependent unsupervised learning strategies, the network can exhibit both discrete and continuous attractor dynamics. A testable prediction based on numerical simulations is that there exist neurons in the brain that can discriminate two similar stimuli at first but cannot after extensive exposure to physically intermediate stimuli. Inspired by this network, we found that adding some local feedbacks to a well-known hierarchical visual recognition model, HMAX, can enable the model to reproduce some recent experimental results related to high-level visual perception.

学科与关键词

关键词
INFERIOR TEMPORAL CORTEXMONKEY INFEROTEMPORAL CORTEXHUMAN VISUAL-SYSTEMASSOCIATIVE MEMORYOBJECT RECOGNITIONPATH-INTEGRATIONNEURAL-NETWORKSSHAPE SELECTIVITYPLACE CELLSREPRESENTATIONS
相关
加载中…
  • Attractor memory with self-organizing input
    Johansson, C; Lansner, ASPRINGER-VERLAG BERLIN,HEIDELBERGER PLATZ 3, D-14197 BERLIN, GERMANY, 2006.被引 6
  • Attractor and integrator networks in the brain
    Khona, Mikail; Fiete, Ila R.*Nature Reviews Neuroscience, 2022, 23(12): 744-766.被引 70
  • Dynamics of Feature Categorization
    Marti, Daniel; Rinzel, JohnNeural Computation, 2013, 25(1): 1-45.被引 8
查看全部 →

发表信息

论文状态
公开发表
期刊
Neural Computation
发表日期
2010-05
卷期
第 22 卷, 第 5 期
页码
1333-1357
DOI
10.1162/neco.2010.02-09-957
语言
ENGLISH
成果收录
SCIE
资助标注
National Natural Science Foundation of China [60805023, 60621062, 60605003]; National Key Foundation RD Project [2003CB317007, 2004CB318108, 2007CB311003]; China Postdoctoral Science Foundation [20080430032, 200801072]; Basic Research Foundation of Tsinghua National Laboratory for Information Science and Technology

作者

  • H

    Hu, Xiaolin (通讯) (第一作者)

    tsinghua univ

  • Z

    Zhang, Bo

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