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 simple probabilistic neural network for machine understanding

Xie, Rongrong; Marsili, Matteo*i
JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT2024-2-29DOI: 10.1088/1742-5468/ad0a8c
7阅读
引用收藏
分享

摘要

We discuss the concept of probabilistic neural networks with a fixed internal representation being models for machine understanding. Here, 'understanding' is interpretted as the ability to map data to an already existing representation which encodes an a priori organisation of the feature space. We derive the internal representation by requiring that it satisfies the principles of maximal relevance and of maximal ignorance about how different features are combined. We show that, when hidden units are binary variables, these two principles identify a unique model-the hierarchical feature model-which is fully solvable and provides a natural interpretation in terms of features. We argue that learning machines with this architecture possess a number of interesting properties, such as the continuity of the representation with respect to changes in parameters and data, the possibility of controlling the level of compression and the ability to support functions that go beyond generalisation. We explore the behaviour of the model with extensive numerical experiments and argue that models in which the internal representation is fixed reproduce a learning modality which is qualitatively different from that of traditional models, such as restricted Boltzmann machines.

学科与关键词

关键词
learning theorymachine learning
相关
加载中…
  • Maximal relevance and optimal learning machines
    Duranthon, O.; Marsili, M.*; Xie, R.JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT, 2021, 2021(3): 033409.被引 6
  • 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
  • Perceptual Learning and Feature-Based Approaches to Concepts – A Critical Discussion
    Richard Stöckle-SchobelFrontiers in Psychology, 2012, 3.
查看全部 →

发表信息

论文状态
公开发表
期刊
JOURNAL OF STATISTICAL MECHANICS-THEORY AND EXPERIMENT
发表日期
2024-02-29
卷期
第 2024 卷, 第 2 期
页码
023403
DOI
10.1088/1742-5468/ad0a8c
语言
ENGLISH
成果收录
SCIE
资助标注
China Scholarship Council (CSC) [202006770018]

作者

  • X

    Xie, Rongrong (第一作者)

    cent china normal univ

  • M

    Marsili, Matteo (通讯)

    i

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