New Methods of Neural Network Training

机译：神经网络训练的新方法

获取原文

页面导航

摘要
著录项
相似文献
相关主题

摘要

New methods for training computational neural networks for dynamic system identification and control have been created, performance of the training algorithms has been analyzed, and the resulting neural networks have been evaluated. Computational neural networks are shown to have excellent potential for identifying the dynamic models of nonlinear systems and for controlling such systems over their entire operating space. Three topics were addressed: (1) Aerodynamic model identification using sigmoid and radial basis function networks; (2) Control of the preferential oxidizer for a fuel cell power system using a neural network Initializing a neural network (nonlinear) controller so that it replicates the characteristics of a gain scheduled linear controller. This research produced new training approaches that will allow future dynamic systems to work with higher accuracy, greater efficiency, and improved reliability.

著录项

作者
Stengel, R. F.;
展开▼
作者单位

展开▼
年度 1999
页码 1-15
总页数 15
原文格式 PDF
正文语种 eng
中图分类工业技术;
关键词
Neural nets; Artificial intelligence; Algorithms; Linear systems; Adaptive control systems; Parallel processing; Nonlinear systems; Computer networks; Computer aided instruction;

机译：神经网络;人工智能;算法;线性系统;自适应控制系统;并行处理;非线性系统;计算机网络;计算机辅助教学;

相似文献

外文文献
中文文献
专利

1. STOCHASTIC GENERALIZED GRADIENT METHODS FOR TRAINING NONCONVEX NONSMOOTH NEURAL NETWORKS [J] . Norkin V. I. Cybernetics and Systems Analysis . 2021,第5期

机译：用于训练非凸起非光华神经网络的随机广义梯度方法
2. Training contextual neural networks with rectifier activation functions: Role and adoption of sorting methods [J] . Huk Maciej Journal of intelligent & fuzzy systems: Applications in Engineering and Technology . 2019,第6aPta1期

机译：培训具有整流激活功能的上下文神经网络：角色和采用排序方法
3. Handwritten Devanagari Character Recognition Using Layer-Wise Training of Deep Convolutional Neural Networks and Adaptive Gradient Methods [J] . Mahesh Jangid, Sumit Srivastava Journal of Imaging . 2018,第2期

机译：深度卷积神经网络的分层明智训练和自适应梯度法的手写体梵文字符识别
4. A non-linear training set superposition filter derived by neural network training methods for implementation in a shift invariant optical correlator [C] . Ioannis Kypraios, Rupert Young, Philip Birch, Conference on Optical Pattern Recognition XIV Apr 24-25, 2003 Orlando, Florida, USA . 2003

机译：通过神经网络训练方法导出的非线性训练集叠加滤波器，用于在位移不变光学相关器中实现
5. Robust Training Methods for Deep Neural Networks with a Variety of Label Noise [D] . Kamabattula, Sree Ram. 2021

机译：具有各种标签噪声的深神经网络的强大培训方法
6. Method for Training Convolutional Neural Networks for In Situ Plankton Image Recognition and Classification Based on the Mechanisms of the Human Eye [O] . Xuemin Cheng, Yong Ren, Kaichang Cheng, 2020

机译：基于人眼机理的卷积神经网络原位浮游生物图像识别与分类训练方法
7. A Training Method for Low Rank Convolutional Neural Networks Based on Alternating Tensor Compose-Decompose Method [O] . Sukho Lee, Hyein Kim, Byeongseon Jeong, 2021

机译：基于交替张量兼容分辨方法的低等级卷积神经网络的训练方法

New Methods of Neural Network Training

摘要

著录项

相似文献

相关主题

期刊订阅