检索结果-内蒙古大学图书馆

Optimization of an artificial neural network for thermal/pressure food processing: Evaluation of training algorithms

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2007年第2期56卷 101-110页

作者： Torrecilla, J. S. Otero, L. Sanz, P. D. Univ Complutense Madrid Dept Chem Engn E-28040 Madrid Spain CSIC Dept Engn E-28040 Madrid Spain

The aim of the current paper is to obtain, through a proper selection of the training algorithm, an optimized artificial neural network (ANN) able to predict two parameters of interest for high-pressure (HP) food processing: the maximum or minimum temperature reached in the sample after pressurization and the time needed for thermal re-equilibration in the high-pressure process. To do that, 13 training algorithms belonging to 4 broad classes (gradient descent, conjugate gradient, quasi-Newton algorithms and Bayesian regularization) have been evaluated by training different ANNs. The network trained with the Levenberg-Marquardt algorithm showed the best overall predictive ability. The performance of this network was subsequently optimized by varying the number of nodes in the hidden layer, the learning coefficient and the decrease factor of this coefficient, and selecting the configuration with the highest predictive ability. The optimized ANN was able to make accurate predictions for the variables studied (temperature and time). These predictions were significantly better than those obtained by a previous ANN developed without selection of the training algorithm, that is, assuming the default option of the ANN computational package (gradient descent with a user-defined learning rate). We have shown that a correct selection of the training algorithm allows maximizing the predictive ability of the artificial neural network. (c) 2007 Elsevier B.V. All rights reserved.

关键词： artificial neural network training algorithm modeling high-pressure thermal control food processing

来源：评论

学校读者我要写书评

暂无评论

Towards Faster training algorithms Exploiting Bandit Sampling From Convex to Strongly Convex Conditions

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2023年第2期7卷 565-577页

作者： Zhou, Yangfan Huang, Kaizhu Cheng, Cheng Wang, Xuguang Hussain, Amir Liu, Xin Univ Sci & Technol China Sch Nanotech & Nanobion Hefei 230026 Anhui Peoples R China Chinese Acad Sci Suzhou Inst Nanotech & NanoBion SINANO Suzhou 215123 Jiangsu Peoples R China Duke Kunshan Univ Data Sci Res Ctr Kunshan 215316 Jiangsu Peoples R China Gusu Lab Mat Suzhou 215123 Jiangsu Peoples R China Edinburgh Napier Univ Sch Comp Edinburgh EH11 4BN Midlothian Scotland

The training process for deep learning and pattern recognition normally involves the use of convex and strongly convex optimization algorithms such as AdaBelief and SAdam to handle lots of "uninformative" samples that should be ignored, thus incurring extra calculations. To solve this open problem, we propose to design bandit sampling method to make these algorithms focus on "informative" samples during training process. Our contribution is twofold: first, we propose a convex optimization algorithm with bandit sampling, termed AdaBeliefBS, and prove that it converges faster than its original version;second, we prove that bandit sampling works well for strongly convex algorithms, and propose a generalized SAdam, called SAdamBS, that converges faster than SAdam. Finally, we conduct a series of experiments on various benchmark datasets to verify the fast convergence rate of our proposed algorithms.

关键词： Bandit sampling convex optimization image processing training algorithm

来源：评论

学校读者我要写书评

暂无评论

Performance comparison of neural network training algorithms in modeling of bimodal drug delivery

引用

INTERNATIONAL JOURNAL OF PHARMACEUTICS 2006年第1-2期327卷 126-138页

作者： Ghaffari, A. Abdollahi, H. Khoshayand, M. R. Bozchalooi, I. Soltani Dadgar, A. Rafiee-Tehrani, M. IASBS Dept Chem Zanjan Iran Univ Tehran Med Sci Sch Pharm Tehran Iran Univ Ottawa Dept Mech Engn Ottawa ON K1N 6N5 Canada

The major aim of this study was to model the effect of two causal factors, i.e. coating weight gain and amount of pectin-chitosan in the coating solution on the in vitro release profile of theophylline for bimodal drug delivery. Artificial neural network (ANN) as a multilayer perceptron feedforward network was incorporated for developing a predictive model of the formulations. Five different training algorithms belonging to three classes: gradient descent, quasi-Newton (Levenberg-Marquardt, LM) and genetic algorithm (GA) were used to train ANN containing a single hidden layer of four nodes. The next objective of the current study was to compare the performance of aforementioned algorithms with regard to predicting ability. The ANNs were trained with those algorithms using the available experimental data as the training set. The divergence of the RMSE between the output and target values of test set was monitored and used as a criterion to stop training. Two versions of gradient descent backpropagation algorithms, i.e. incremental backpropagation (IBP) and batch backpropagation (BBP) outperformed the others. No significant differences were found between the predictive abilities of IBP and BBP, although, the convergence speed of BBP is three- to four-fold higher than IBP. Although, both gradient descent backpropagation and LM methodologies gave comparable results for the data modeling, training of ANNs with genetic algorithm was erratic. The precision of predictive ability was measured for each training algorithm and their performances were in the order of: IBP, BBP > LM > QP (quick propagation) > GA. According to BBP-ANN implementation, an increase in coating levels and a decrease in the amount of pectin-chitosan generally retarded the drug release. Moreover, the latter causal factor namely the amount of pectin-chitosan played slightly more dominant role in determination of the dissolution profiles. (c) 2006 Elsevier B.V. All rights reserved.

关键词： artificial neural network (ANN) bimodal drug delivery genetic algorithm (GA) gradient descent algorithm Levenberg-Marquardt (LM) algorithm modeling training algorithm

来源：评论

学校读者我要写书评

暂无评论

Landslide susceptibility mapping at Ovack-Karabuk (Turkey) using different artificial neural network models: comparison of training algorithms

引用

BULLETIN OF ENGINEERING GEOLOGY AND THE ENVIRONMENT 2019年第1期78卷 89-102页

作者： Can, Asli Dagdelenler, Gulseren Ercanoglu, Murat Sonmez, Harun Hacettepe Univ Dept Geol Engn TR-06800 Ankara Turkey

This study aims to investigate the performances of different training algorithms used for an artificial neural network (ANN) method to produce landslide susceptibility maps. For this purpose, Ovack region (southeast of Karabuk Province), located in the Western Black Sea Region (Turkey), was selected as the study area. A total of 196 landslides were mapped, and a landslide database was prepared. Topographical elevation, slope angle, aspect, wetness index, lithology, and vegetation index parameters were taken into account for the landslide susceptibility analyses. Two different ANN structures, which were composed of single and double hidden layers, were applied to compare the effects of the ANN. Four different training algorithms, namely batch back-propagation, quick propagation, conjugate gradient descent (CGD), and Levenberg-Marquardt, were used for the training stage of the ANN models. Thus, eight different landslide susceptibility maps were produced for the study area using different ANN structures and algorithms. In order to assess the effects and spatial performances of the considered training algorithms on the ANN models, the relative operating characteristics (ROC) and relation value (r(ij)) approaches were used. The susceptibility map produced by CGD1 has the highest AUC (0.817) and r(ij) values (0.972). Comparison of the susceptibility maps indicated that CGD training algorithm is the slowest one among the other algorithms, but this algorithm showed the highest performance on the results.

关键词： Artificial neural network Landslide susceptibility map Ovack (Karabuk) training algorithm

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Neural Network training algorithms and Support Vector Machine for Power Generation Forecast of Photovoltaic Panel

引用

IEEE LATIN AMERICA TRANSACTIONS 2017年第6期15卷 1091-1100页

作者： da Silva, T. V. Monteiro, R. V. A. Guimaraes, G. C. Moura, F. A. M. Albertini, M. R. M. C. Tamashiro, M. A. Univ Fed Uberlandia Dept Engn Eletr Uberlandia MG Brazil Univ Fed Uberlandia Programa Pos Grad Engn Eletr Uberlandia MG Brazil Univ Fed Uberlandia Uberlandia MG Brazil Univ Fed Triangulo Mineiro Dept Engn Eletr Uberaba Brazil Univ Fed Triangulo Mineiro Uberaba Brazil Inst Fed Tocantins IFTO Palmas Brazil

Current energy policies are encouraging the connection of power generation based on low-polluting technologies, mainly those using renewable sources to distribution networks. The photovoltaic (PV) systems have experienced a great growth around the word in last years. Hence, it becomes increasingly important to understand technical challenges, facing high penetration of PV systems at the grid, especially considering the effects of intermittence of this source on the power quality, reliability and stability of the electric distribution system. In another hand, the connections of distributed generators, by PV panels, changes voltage profile at low voltage power systems. This fact can affect the distribution networks on which they are attached causing overvoltage, undervoltage, frequency oscillations and changes in protection design. In order to predict these disturbs, because of this PV penetration, this article aims to analyze seven training algorithms used in artificial neural networks for temporal prediction of the generated active power and thus the state of the distribution network in which these microgenerators are connected and, then compare its best results with the Support Vector Machine (SVM) technique. As a result it was concluded that 3 algorithms are suitable for this type of analysis with the best performance among the seven analyzed was the Bayesian Regularization and that Artificial Neural Networks are more suitable for this problem than the SVM.

关键词： training algorithm Artificial Neural Network Support Vector Machine Photovoltaic penetration Microgeneration Power Quality

来源：评论

学校读者我要写书评

暂无评论

Effective training algorithms for RBF-neural networks

引用

NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT 2003年第2-3期502卷 529-531页

作者： Ososkov, G Stadnik, A Joint Inst Nucl Res Dubna 141980 Moscow Region Russia Ivanovo State Univ Ivanovo 153377 Russia

New structure and training algorithms of the RBF-type neural network are proposed. An extra neuron layer is added to realize the principal component method. A novel training algorithm is designed for training each separate neuron in the hidden layer, which guarantees the efficiency and finiteness of the training procedure. Results were obtained for a variety of problems. In particular, the results of human face recognition look very promising. (C) 2003 Elsevier Science B.V. All rights reserved.

关键词： neural network training algorithm face recognition

来源：评论

学校读者我要写书评

暂无评论

Selection of Network Parameters in Direct ANN Modeling of Roughness Obtained in FFF Processes

引用

POLYMERS 2025年第1期17卷 120-120页

作者： Buj-Corral, Irene Sivatte-Adroer, Maurici Rodero-de-Lamo, Lourdes Marco-Almagro, Lluis Univ Politecn Cataluna Barcelona Sch Ind Engn ETSEIB Dept Mech Engn Ave Diagonal 647 Barcelona 08028 Spain Univ Politecn Cataluna Polytech Sch Engn Vilanova & Geltru EPSEVG Dept Mech Engn Ave Victor Balaguer 1 Vilanova I La Geltru 08880 Spain Univ Politecn Catalunya UPC Barcelona Sch Ind Engn ETSEIB Dept Stat & Operat Res Av Diagonal 647 Barcelona 08028 Spain

Artificial neural network (ANN) models have been used in the past to model surface roughness in manufacturing processes. Specifically, different parameters influence surface roughness in fused filament fabrication (FFF) processes. In addition, the characteristics of the networks have a direct impact on the performance of the models. In this work, a study about the use of ANN to model surface roughness in FFF processes is presented. The main objective of the paper is discovering how key ANN parameters (specifically, the number of neurons, the training algorithm, and the percentage of training and validation datasets) affect the accuracy of surface roughness predictions. To address this question, 125 3D printing experiments were conducted changing orientation angle, layer height and printing temperature, and measuring average roughness Ra as response. A multilayer perceptron neural network model with backpropagation algorithm was used. The study evaluates the effect of three ANN parameters: (1) number of neurons in the hidden layer (4, 5, 6 or 7), (2) training algorithm (Levenberg-Marquardt, Resilient Backpropagation or Scaled Conjugate Gradient), and (3) data splitting ratios (70%-15%-15% vs. 55%-15%-30%). Mean Absolute Error (MAE) was used as the performance metric. The Resilient Backpropagation algorithm, 7 neurons, and using 55% of training data yielded the best predictive performance, minimizing the MAE. Additionally, the impact of the dataset size on prediction accuracy was analysed. It was observed that the performance of the ANN gets worse as the number of datasets is reduced, emphasizing the importance of having sufficient data. This study will help to select appropriate values for the printing parameters in FFF processes, as well as to define the characteristics of the ANN to be used to model surface roughness.

关键词： FFF FDM Polylactic acid artificial neural networks surface roughness training algorithm number of neurons datasets distribution multilayer perceptron backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Effective training algorithms for RBF-neural networks

Effective training algorithms for RBF-neural networks

引用

8th International Workshop on Advanced Computing and Analysis Techniques in Physics Research (ACAT 2002)

作者： Ososkov, G Stadnik, A Joint Inst Nucl Res Dubna 141980 Moscow Region Russia Ivanovo State Univ Ivanovo 153377 Russia

关键词： neural network training algorithm face recognition

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of MLPFF Neural Network Back propagation training algorithms for Time Series Data

Performance Analysis of MLPFF Neural Network Back propagatio...

引用

World Congress on Computing and Communication Technologies (WCCCT)

作者： Kumar, Ashok Murugan, S. Govt Arts Coll Dept Comp Sci Tiruchirappalli Tamil Nadu India Alagappa Govt Arts Coll Dept Comp Sci Karaikkudi Tamil Nadu India

ISBN: (纸本)9781479928767

This paper investigates the various training algorithm with Multi-Layer Perceptron Feed Forward Neural Network (MLPFFNN) and identify the best training algorithm for Indian Stock Exchange Market especially for BSE100 and NIFTY MIDCAP50. The forecasting accuracy is analyzed and measured with reference to an Indian stock market index such as Bombay Stock Exchange (BSE) and NIFTY MIDCAP50 in this study and it is found that the best training algorithm is Levenberg-Marquardt. All training algorithms uses the 1-5-1 MLPFFNN architecture and its various parameter such as epochs, learning rate, etc are studied and the results are tabulated for the data division ratio 60%, 20% and 20% which represents training, validating and testing for all training algorithm.

关键词： Time serie Neural Network forecasting training algorithm stock market

来源：评论

学校读者我要写书评

暂无评论

An algorithm for training a class of polynomial models

引用

DIGITAL SIGNAL PROCESSING 2023年第1期141卷

作者： Popescu, Marius-Claudiu Grama, Lacrimioara Rusu, Corneliu Tech Univ Cluj Napoca Fac Elect Telecommun & Informat Technol Signal Proc Grp 26-28 G Baritiu St Cluj Napoca 400027 Romania

In this paper we propose a new training algorithm for a class of polynomial models. The algorithm is derived using a learning bound for predictors that are convex combinations of functions from simpler classes. In our case, the hypotheses are polynomials over the input features, and they are interpreted as convex combinations of homogeneous polynomials. In addition, the coefficients are restricted to be positive and to sum to 1. This constraint will simplify the interpretation of the model. The training is done by minimizing a surrogate of the learning bound, using an iterative two-phase algorithm. Basically, in the first phase the algorithm decides which monomials of higher degree should be added, and in the second phase the coefficients are recomputed by solving a convex program. We performed several experiments on binary classification datasets from different domains. Experiments show that the algorithm compares favorably in terms of accuracy and speed with other classification methods, including some new interpretable methods like Neural Additive Models and CORELS. In addition, the resulting predictor can sometimes be understood and validated by a domain expert. The code is publicly available.& COPY;2023 Elsevier Inc. All rights reserved.

关键词： Polynomial models training algorithm Learning bounds Interpretable model

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：