Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

Search research articles

相关实验视频

Updated: Jan 12, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

浅层和集体深度随机神经网络用于异常检测.

Anuradha Kumari¹, A K Malik¹, M Tanveer¹

¹Department of Mathematics, Indian Institute of Technology Indore, Simrol, Indore, 453552, Madhya Pradesh, India.

Neural networks : the official journal of the International Neural Network Society

|November 7, 2025

概括

我们介绍一级组合深度RVFL (OC-edRVFL),一个先进的异常检测模型. 这种新的方法提高了大型数据集的稳定性和概括性,优于传统方法.

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Heterogeneous oblique double random forest.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

EDA-OCBLS: An error-distribution aware one-class broad learning system for anomaly detection.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

A comprehensive review of use cases, misuses, and potential mitigation techniques in generative artificial intelligence.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

Dual-center RAPID-LSSVM: Radius-adaptive, probability and imbalance driven weighting for Alzheimer's diagnosis.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

Nanotherapeutic strategies for mitigating sepsis-induced multiorgan dysfunctions.

Nanomedicine (London, England)·2026

Same author

A robust multi-view support vector machine with the RoBoSS loss function.

Neural networks : the official journal of the International Neural Network Society·2026

科学领域:

机器学习机器学习
人工智能的人工智能
数据科学数据科学数据科学

背景情况:

异常检测或一类分类 (OCC) 对于现实应用至关重要.
传统的基于支向量的机器OCC模型与大数据集和内核灵敏度作斗争.
现有的模型通常在捕捉复杂模式方面存在局限性,原因是单个隐藏层.

研究的目的:

为增强异常检测提出新的深度学习模型.
克服传统OCC方法的局限性,特别是大规模数据集.
提高一类分类模型的概括性,稳定性和稳定性.

主要方法:

引入一类随机向量功能链路 (OC-RVFL) 网络,融合线性和非线性模式.
通过将深度学习和集体学习与OC-RVFL集成,开发一类集体深度RVFL (OC-edRVFL).
使用封闭式解决方案进行高效的输出重量计算并推导泛化误差极限.

主要成果:

与OC-RVFL相比,OC-edRVFL模型表现出优越的稳定性,稳定性和通用性.
对各种数据集 (人工,UCI,NDC,MNIST) 的实验表明,OC-edRVFL的表现优于基线模型.
提出的模型在最多500万个样本的数据集上表现出高性能.

关键词:

深度学习是一种深度学习.组合深度RVFL的组合组合学习学习组合学习具有多个输出层的神经网络.一个类别的分类分类.随机向量功能链路 (RVFL) 网络网络.

更多相关视频

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

相关实验视频

Last Updated: Jan 12, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

结论:

OC-edRVFL是一种高效且可扩展的异常检测解决方案.
这种新的深层合奏方法显著提升了一类分类的功能.
这些模型减少了培训时间,并提高了大型复杂数据集的性能.