首页> 外文学位 >Perturbed neural network backpropagation learning and adaptive wavelets for dimension reduction for improved classification of high-dimensional datasets.

【24h】

Perturbed neural network backpropagation learning and adaptive wavelets for dimension reduction for improved classification of high-dimensional datasets.

机译：扰动神经网络的反向传播学习和自适应小波用于降维，以改进高维数据集的分类。

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

In this work we propose a two-part process aimed at reducing the computational load and retaining the classification accuracies of neural networks applied to high-dimensional datasets of remotely-sensed data---hyperspectral imagery. First, we compute a set of near-optimum adaptive wavelets that depend on the covariance of the data, which are then employed to reduce the dimensionality of the data. Such dimension reduction linear transformation has several desirable properties. Secondly, we discuss two different types of modifications to the backpropagation learning rule that tend to decrease the convergence error rates and increase the neural network's classification accuracy. We show that the combination of the dimension reduction method and the modified backpropagation learning rule produce neural networks with generalization capabilities comparable to those where these methods have not been employed. We also discuss how a particular set of target vectors has a positive effect on the error and convergence of the discussed backpropagation algorithms. Finally, we test these techniques on remotely-sensed hyperspectral imagery for classification purposes.

机译：在这项工作中，我们提出了一个分为两部分的过程，旨在减少计算负荷并保留应用于遥感数据-高光谱图像的高维数据集的神经网络的分类精度。首先，我们根据数据的协方差计算一组接近最佳的自适应小波，然后将其用于降低数据的维数。这种降维线性变换具有几个期望的特性。其次，我们讨论了对反向传播学习规则的两种不同类型的修改，这些修改往往会降低收敛误差率并提高神经网络的分类精度。我们表明，降维方法和改进的反向传播学习规则的组合产生的神经网络的泛化能力可与未使用这些方法的神经网络相比。我们还将讨论一组特定的目标向量如何对所讨论的反向传播算法的误差和收敛产生积极影响。最后，出于分类目的，我们在遥感高光谱图像上测试了这些技术。

著录项

作者
Bosch, Edward H.;
展开▼
作者单位

George Mason University.;

展开▼
授予单位 George Mason University.;
学科 Mathematics.
学位 Ph.D.
年度 2005
页码 232 p.
总页数 232
原文格式 PDF
正文语种 eng
中图分类数学;
关键词

相似文献

外文文献
中文文献
专利

1. Power Function Error Initialization Can Improve Convergence of Backpropagation Learning in Neural Networks for Classification [J] . Andreas Knoblauch Neural computation . 2021,第8期

机译：功率函数错误初始化可以提高神经网络中的反向化学习的收敛性分类
2. Fast and improved backpropagation learning of multi-layer artificial neural network using adaptive activation function [J] . Panda Sashmita, Panda Ganapati Expert Systems . 2020,第5期

机译：使用自适应激活函数快速和改进多层人工神经网络的反向学习
3. Wavelet Neural Networks, Elman Backpropagation and Multilayer Perceptrons for Epilepsy Classification from EEG Signals [J] . Harikumar Rajaguru, Sunil Kumar Prabhakar Research journal of pharmacy and technology . 2018,第4期

机译：小波神经网络，Elman Backpropagation和MuGPilepsy来自EEG信号分类的多层感知
4. Distributed Learning of Deep Sparse Neural Networks for High-dimensional Classification [C] . Shweta Garg, R. Krishnan, S. Jagannathan, IEEE International Conference on Big Data . 2018

机译：用于高维分类的深度稀疏神经网络的分布式学习
5. Neural networks and adaptive wavelets for vector quantization, function approximation, and classification. [D] . Campos, Marcos de Moura. 2002

机译：用于矢量量化，函数逼近和分类的神经网络和自适应小波。
6. Sex Determination of Three-Dimensional Skull Based on Improved Backpropagation Neural Network [O] . Wen Yang, Xiaoning Liu, Kegang Wang, 2019

机译：基于改进BP神经网络的三维颅骨性别确定
7. Feature extraction and artificial neural networks for the on-the-fly classification of high-dimensional thermochemical spaces in adaptive-chemistry simulations – ERRATUM [O] . Giuseppe D’Alessio, Alberto Cuoci, Alessandro Parente 2021

机译：特征提取和人工神经网络，用于自适应化学模拟中的高维热化学空间的开蝇分类 - 误斗

Perturbed neural network backpropagation learning and adaptive wavelets for dimension reduction for improved classification of high-dimensional datasets.

摘要

著录项

相似文献

相关主题

期刊订阅