• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

Enhanced training algorithms, and integrated training/architecture selection for multilayer perceptron networks.

作者信息

Bello M G

机构信息

Charles Stark Draper Lab. Inc., Cambridge, MA.

出版信息

IEEE Trans Neural Netw. 1992;3(6):864-75. doi: 10.1109/72.165589.

DOI:10.1109/72.165589
PMID:18276484
Abstract

The standard backpropagation-based multilayer perceptron training algorithm suffers from a slow asymptotic convergence rate. Sophisticated nonlinear least-squares and quasi-Newton optimization techniques are used to construct enhanced multilayer perceptron training algorithms, which are then compared to the backpropagation algorithm in the context of several example problems. In addition, an integrated approach to training and architecture selection that uses the described enhanced algorithms is presented, and its effectiveness illustrated in the context of synthetic and actual pattern recognition problems.

摘要

相似文献

1
Enhanced training algorithms, and integrated training/architecture selection for multilayer perceptron networks.
IEEE Trans Neural Netw. 1992;3(6):864-75. doi: 10.1109/72.165589.
2
Fast training of multilayer perceptrons.多层感知器的快速训练
IEEE Trans Neural Netw. 1997;8(6):1314-20. doi: 10.1109/72.641454.
3
Improved training of neural networks for the nonlinear active control of sound and vibration.用于声音和振动非线性主动控制的神经网络改进训练。
IEEE Trans Neural Netw. 1999;10(2):391-401. doi: 10.1109/72.750568.
4
Optimized approximation algorithm in neural networks without overfitting.神经网络中无过拟合的优化近似算法。
IEEE Trans Neural Netw. 2008 Jun;19(6):983-95. doi: 10.1109/TNN.2007.915114.
5
An accelerated learning algorithm for multilayer perceptrons: optimization layer by layer.一种用于多层感知器的加速学习算法：逐层优化
IEEE Trans Neural Netw. 1995;6(1):31-42. doi: 10.1109/72.363452.
6
Parameter incremental learning algorithm for neural networks.神经网络的参数增量学习算法
IEEE Trans Neural Netw. 2006 Nov;17(6):1424-38. doi: 10.1109/TNN.2006.880581.
7
Hybrid Training Method for MLP: Optimization of Architecture and Training.多层感知器的混合训练方法：架构与训练的优化
IEEE Trans Syst Man Cybern B Cybern. 2011 Aug;41(4):1097-109. doi: 10.1109/TSMCB.2011.2107035. Epub 2011 Feb 10.
8
An accelerated learning algorithm for multilayer perceptron networks.一种用于多层感知器网络的加速学习算法。
IEEE Trans Neural Netw. 1994;5(3):493-7. doi: 10.1109/72.286921.
9
A second-order learning algorithm for multilayer networks based on block Hessian matrix.一种基于块海森矩阵的多层网络二阶学习算法。
Neural Netw. 1998 Dec;11(9):1607-1622. doi: 10.1016/s0893-6080(98)00091-4.
10
An optimization methodology for neural network weights and architectures.一种针对神经网络权重和架构的优化方法。
IEEE Trans Neural Netw. 2006 Nov;17(6):1452-9. doi: 10.1109/TNN.2006.881047.

引用本文的文献

1
Modeling of thermodynamic and physico-chemical properties of coumarins bioactivity against Candida albicans using a Levenberg-Marquardt neural network.使用Levenberg-Marquardt神经网络对香豆素抗白色念珠菌生物活性的热力学和物理化学性质进行建模。
Adv Appl Bioinform Chem. 2010;3:59-66. doi: 10.2147/aabc.s11812. Epub 2010 Aug 13.