Optimized Approximation Algorithm in Neural Networks Without Overfitting

Liu Y.; Starzyk J. A.; Zhu Z.

首页> 外文期刊>IEEE Transactions on Neural Networks >Optimized Approximation Algorithm in Neural Networks Without Overfitting

【24h】

Optimized Approximation Algorithm in Neural Networks Without Overfitting

机译：无过度拟合的神经网络优化逼近算法

获取原文

获取原文并翻译 | 示例

获取外文期刊封面封底 >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

In this paper, an optimized approximation algorithm (OAA) is proposed to address the overfitting problem in function approximation using neural networks (NNs). The optimized approximation algorithm avoids overfitting by means of a novel and effective stopping criterion based on the estimation of the signal-to-noise-ratio figure (SNRF). Using SNRF, which checks the goodness-of-fit in the approximation, overfitting can be automatically detected from the training error only without use of a separate validation set. The algorithm has been applied to problems of optimizing the number of hidden neurons in a multilayer perceptron (MLP) and optimizing the number of learning epochs in MLP''s backpropagation training using both synthetic and benchmark data sets. The OAA algorithm can also be utilized in the optimization of other parameters of NNs. In addition, it can be applied to the problem of function approximation using any kind of basis functions, or to the problem of learning model selection when overfitting needs to be considered.

机译：在本文中，提出了一种优化的近似算法（OAA），以解决使用神经网络（NN）进行函数逼近的过拟合问题。优化的近似算法通过基于信噪比（SNRF）的估计的新颖有效的停止准则来避免过拟合。使用SNRF来检查近似值的拟合优度，只有在不使用单独的验证集的情况下，才可以从训练误差中自动检测出过度拟合。该算法已应用于优化多层感知器（MLP）中的隐藏神经元数量以及使用合成和基准数据集优化MLP的反向传播训练中学习时期的数量的问题。 OAA算法也可用于优化NN的其他参数。另外，它可以应用于使用任何一种基函数的函数逼近问题，或者在需要考虑过度拟合时应用于学习模型选择的问题。

著录项

来源
《IEEE Transactions on Neural Networks》 |2008年第6期|p.983-995|共13页
作者
Liu Y.; Starzyk J. A.; Zhu Z.;
展开▼
作者单位

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类自动化技术、计算机技术;
关键词

相似文献

外文文献
中文文献
专利

1. An Algorithm For Training Multilayer Perceptron (MLP) For Image Reconstruction Using Neural Network Without Overfitting. [J] . Mohammad Mahmudul Alam Mia, Shovasis Kumar Biswas, Monalisa Chowdhury Urmi, International Journal of Scientific & Technology Research . 2015,第2期

机译：一种使用神经网络训练多层感知器（MLP）进行图像重建的算法，而无需过度拟合。
2. Optimization of Laser Ablation Technology for PDPhSM Matrix Nanocomposite Thin Film by Artificial Neural Networks-particle Swarm AlgorithmOptimization of Laser Ablation Technology for PDPhSM Matrix Nanocomposite Thin Film by Artificial Neural Networks-particle Swarm AlgorithmOptimization of Laser Ablation Technology for PDPhSM Matrix Nanocomposite Thin Film by Artificial Neural Networks-particle Swarm Algorithm [J] . TANG Puhong, SONG Renguo, CHAI Guozhong, 武汉理工大学学报：材料科学英文版 . 2010,第002期

机译：人工神经网络优化PDPhSM纳米复合薄膜的激光烧蚀技术-粒子群算法人工神经网络优化PDPhSM纳米复合薄膜的激光烧蚀技术-人工神经网络优化PDPhSM纳米复合薄膜的激光烧蚀技术网络粒子群算法
3. Data from multimodal functions based on an array of photovoltaic modules and an approximation with artificial neural networks as a scenario for testing optimization algorithms [J] . Carlos Robles-Algarín, Diego Restrepo-Leal, Adalberto Ospino Castro Data in Brief . 2019,第23期

机译：来自基于光伏模块阵列的多峰函数的数据，以及人工神经网络的近似值作为测试优化算法的场景
4. Feasibility study of using artificial neural networks for approximation of n-dimensional obj ective functions in memetic algorithms for structural optimization [C] . Peter Pechac, Milan Saga, Peter Weis International Scientific Conference of Young Scientists on Sustainable, Modern and Safe Transport . 2017

机译：使用人工神经网络的可行性研究，用于近似结构优化中的N维OBJ异常功能的近似
5. Stochastic Optimization Based on White-Box Deterministic Approximations: Models, Algorithms and Application to Service Networks [D] . Krishnamoorthy, Mohan. 2018

机译：基于白盒确定性近似的随机优化：模型，算法及其在服务网络中的应用
6. Data from multimodal functions based on an array of photovoltaic modules and an approximation with artificial neural networks as a scenario for testing optimization algorithms [O] . Carlos Robles-Algarín, Diego Restrepo-Leal, Adalberto Ospino Castro 2019

机译：来自基于光伏模块阵列的多峰函数的数据以及人工神经网络的近似值作为测试优化算法的场景
7. Data from multimodal functions based on an array of photovoltaic modules and an approximation with artificial neural networks as a scenario for testing optimization algorithms [O] . Carlos Robles-Algarín, Diego Restrepo-Leal, Adalberto Ospino Castro 2019

机译：基于光伏模块阵列的多模式函数的数据以及与人工神经网络的近似作为测试优化算法的场景
8. Hierarchical Neural Network Based Data Processing System for Ground- Penetrating Radar. An End of Year Report for CH/1049/6: Application of Neural Networks Coupled With Genetic Algorithms to Optimize Soil Cleanup Operations in Cold Climates [R] . Sullivan, J. M. 1997

机译：基于分层神经网络的探地雷达数据处理系统。 CH / 1049/6的年终报告：神经网络与遗传算法相结合的应用，以优化寒冷气候下的土壤清理作业

Optimized Approximation Algorithm in Neural Networks Without Overfitting

摘要

著录项

相似文献

相关主题

期刊订阅