检索结果-内蒙古大学图书馆

CAST: A constant Adaptive Skipping training algorithm for Improving the Learning Rate of Multilayer Feedforward Neural Networks

引用

Research Journal of Applied Sciences, Engineering and Technology 2016年第8期12卷 790-812页

作者： R. Manjula Devi S. Kuppuswami Faculty of Computer Science and Engineering Kongu Engineering College Perundurai Erode

Multilayer Feedforward Neural Network (MFNN) has been administered widely for solving a wide range of supervised pattern recognition tasks. The major problem in the MFNN training phase is its long training time especially when it is trained on very huge training datasets. In this accordance, an enhanced training algorithm called Constant Adaptive Skipping training (CAST) algorithm is proposed in this research paper which intensifies on reducing the training time of the MFNN through stochastic manifestation of training datasets. The stochastic manifestation is accomplished by partitioning the training dataset into two completely separate classes, classified and misclassified class, based on the comparison result of the calculated error measure with the threshold value. Only the input samples in the misclassified class are exhibited to the MFNN for training in the next epoch, whereas the correctly classified class is skipped constantly which dynamically reducing the number of training input samples exhibited at every single epoch. Thus decreasing the size of the training dataset constantly can reduce the total training time, thereby speeding up the training process. This CAST algorithm can be merged with any training algorithms used for supervised task, can be used to train the dataset with any number of patterns and also it is very simple to implement. The evaluation of the proposed CAST algorithm is demonstrated effectively using the benchmark datasets - Iris, Waveform, Heart Disease and Breast Cancer for different learning rate. Simulation study proved that CAST training algorithm results in faster training than LAST and standard BPN algorithm.

关键词： Adaptive skipping learning rate MFNN neural network training algorithm training speed

来源：评论

学校读者我要写书评

暂无评论

A homotopy training algorithm for fully connected neural networks

引用

PROCEEDINGS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES 2019年第2231期475卷 1-19页

作者： Chen, Qipin Hao, Wenrui Penn State Univ Dept Math University Pk PA 16802 USA

In this paper, we present a homotopy training algorithm (HTA) to solve optimization problems arising from fully connected neural networks with complicated structures. The HTA dynamically builds the neural network starting from a simplified version and ending with the fully connected network via adding layers and nodes adaptively. Therefore, the corresponding optimization problem is easy to solve at the beginning and connects to the original model via a continuous path guided by the HTA, which provides a high probability of obtaining a global minimum. By gradually increasing the complexity of the model along the continuous path, the HTA provides a rather good solution to the original loss function. This is confirmed by various numerical results including VGG models on CIFAR-10. For example, on the VGG13 model with batch normalization, HTA reduces the error rate by 11.86% on the test dataset compared with the traditional method. Moreover, the HTA also allows us to find the optimal structure for a fully connected neural network by building the neutral network adaptively.

关键词： homotopy method training algorithm machine learning neural network

来源：评论

学校读者我要写书评

暂无评论

Comparison of the Classical algorithm with the training algorithm in Scheduling Problem ADI Production

引用

ARCHIVES OF FOUNDRY ENGINEERING 2022年第1期22卷 5-12页

作者： Wilk-Kolodziejczyk, D. Chrzan, K. Jaskowiec, K. Pirowski, Z. Zuczek, R. Bitka, A. Machulec, D. AGH Univ Sci & Technol Krakow Poland Lukasiewicz Res Network Krakow Inst Technol Krakow Poland

A classical algorithm Tabu Search was compared with Q Learning (named learning) with regards to the scheduling problems in the Austempered Ductile Iron (ADI) manufacturing process. The first part comprised of a review of the literature concerning scheduling problems, machine learning and the ADI manufacturing process. Based on this, a simplified scheme of ADI production line was created, which a scheduling problem was described for. Moreover, a classic and training algorithm that is best suited to solve this scheduling problem was selected. In the second part, was made an implementation of chosen algorithms in Python programming language and the results were discussed. The most optimal algorithm to solve this problem was identified. In the end, all tests and their results for this project were presented.

关键词： Production scheduling Austempered Ductile Iron Iron castings Foundry industry training algorithm Tabu search

来源：评论

学校读者我要写书评

暂无评论

A Global Convergence PSO training algorithm of Neural Networks

A Global Convergence PSO Training Algorithm of Neural Networ...

引用

8th World Congress on Intelligent Control and Automation (WCICA)

作者： Li, Ming Li, Wei Yang, Cheng-wu Southwest Forestry Univ Coll Commun Machinery & Civil Engn Kunming Yunnan Peoples R China Nanjing Univ Sci & Technol Coll Power Engn Nanjing Jiangsu Peoples R China

ISBN: (纸本)9781424467129

Traditional gradient-based training algorithms have been known to suffer from local minima and have heavy computation load for obtaining the derivative information. The particle swarm optimization (PSO) method was used as a training algorithm of neural networks to improve the convergence rate. However, as the network architecture grows, the size of swarm increases exponentially, which increase the computational complexity evidently. Moreover, such algorithms had the problem of premature convergence. An improved PSO training algorithm was proposed in this paper. The swarm was only composed of two particles in the new algorithm. The algorithm was guaranteed to converge to the global optimization solution with probability one. Simulation results show the new algorithm has fast convergence rate and high accuracy. Moreover, the convergence of the algorithm didn't depend on the initial value of weights of neural networks.

关键词： neural network training algorithm PSO algorithm global convergence

来源：评论

学校读者我要写书评

暂无评论

The Improved training algorithm of Back Propagation Neural Network with Self-adaptive Learning Rate

The Improved Training Algorithm of Back Propagation Neural N...

引用

2009 International Conference on Computational Intelligence and Natural Computing(CINC 2009)

作者： Yong Li, Yang Fu, Hui Li and Si-Wen Zhang School of Energy Resources and Mechanical Engineering Northeast Dianli University Jilin City, China

This paper addresses the questions of improving convergence performance for back propagation (BP) neural network. For traditional BP neural network algorithm, the learning rate selection is depended on experience and trial. In this paper, based on Taylor formula the function relationship between the total quadratic training error change and connection weights and biases changes is obtained, and combined with weights and biases changes in batch BP learning algorithm, the formula for self-adaptive learning rate is given. Unlike existing algorithm, the self-adaptive learning rate depends on only neural network topology, training samples, average quadratic error and error curve surface gradient but not artificial selection. Simulation results show iteration times is significant less than that of traditional batch BP learning algorithm with constant learning rate.

关键词： artificial neural network back propagation neural network training algorithm learning rate self-adaptive

来源：评论

学校读者我要写书评

暂无评论

The assessment of Levenberg-Marquardt and Bayesian Framework training algorithm for prediction of concrete shrinkage by the artificial neural network

引用

COGENT ENGINEERING 2019年第1期6卷 Article: 1609179页

作者： Garoosiha, Hosein Ahmadi, Jamal Bayat, Hossein Univ Zanjan Fac Engn Dept Civil Engn Zanjan Iran

Shrinkage and creep are the main concrete volume changes over time. This unacceptable concrete deformation leads to stress and cracks creation where eventually reduces the service life of concrete structures. According to this, the prediction of shrinkage and creep strain in concrete structures with acceptable accuracy is the significance essential. The extensive investigation accomplished by several researchers has created different relationships and models for forecasting of shrinkage and creep strain based on experimental and analytical observation. Despite effective efforts in this regard, existing models do not have sufficient accuracy for anticipate of shrinkage strain. According to this, in this research, it has been attempted to provide a shrinkage predicting model based on the artificial neural network technique with the application of RILEM database. Also, it has been tried to determine the accuracy of the proposed model in comparison to the existing standard models by statistical analysis. According to the obtained results, by application of the neural network technique, the shrinkage strain could be predicted with acceptable accuracy especial in the extended period.

关键词： shrinkage strains prediction models artificial neural network training algorithm modern concrete

来源：评论

学校读者我要写书评

暂无评论

Modulation spectrum-constrained trajectory training algorithm for GMM-based Voice Conversion

Modulation spectrum-constrained trajectory training algorith...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： S. Takamichi T. Toda A. W. Black S. Nakamura Grad. Sch. of Inf. Sci. Nara Inst. of Sci. & Technol. (NAIST) Nara Japan

ISBN: (纸本)9781467369985

This paper presents a novel training algorithm for Gaussian Mixture Model (GMM)-based Voice Conversion (VC). One of the advantages of GMM-based VC is computationally efficient conversion processing enabling to achieve real-time VC applications. On the other hand, the quality of the converted speech is still significantly worse than that of natural speech. In order to address this problem while preserving the computationally efficient conversion processing, the proposed training method enables 1) to use a consistent optimization criterion between training and conversion and 2) to compensate a Modulation Spectrum (MS) of the converted parameter trajectory as a feature sensitively correlated with over-smoothing effects causing quality degradation of the converted speech. The experimental results demonstrate that the proposed algorithm yields significant improvements in term of both the converted speech quality and the conversion accuracy for speaker individuality compared to the basic training algorithm.

关键词： GMM-based voice conversion modulation spectrum over-smoothing training algorithm modulation spectra e-bank vital capacity measurement training methods optimal criterion Speech Voice trajectory Functional training

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

Neural networks trained by weight permutation are universal approximators

引用

NEURAL NETWORKS 2025年 187卷 107277页

作者： Cai, Yongqiang Chen, Gaohang Qiao, Zhonghua Beijing Normal Univ Sch Math Sci Lab Math & Complex Syst MOE Beijing 100875 Peoples R China Hong Kong Polytech Univ Dept Appl Math Hung Hom Kowloon Hong Kong Peoples R China Hong Kong Polytech Univ Inst Smart Energy Dept Appl Math & Res Hung HomKowloon Hong Kong Peoples R China

The universal approximation property is fundamental to the success of neural networks, and has traditionally been achieved by training networks without any constraints on their parameters. However, recent experimental research proposed a novel permutation-based training method, which exhibited a desired classification performance without modifying the exact weight values. In this paper, we provide a theoretical guarantee of this permutation training method by proving its ability to guide a ReLU network to approximate onedimensional continuous functions. Our numerical results further validate this method's efficiency in regression tasks with various initializations. The notable observations during weight permutation suggest that permutation training can provide an innovative tool for describing network learning behavior.

关键词： Universal approximation property Neural networks training algorithm Learning behavior

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic multi-objective optimization with artificial neural networks surrogate modeling for optimal energy-economic performance for CSP technology

ENERGY AND AI

引用

ENERGY AND AI 2025年 20卷

作者： Allouhi, A. Amine, M. Benzakour Aoul, K. A. Tabet USMBA Ecole Super Technol Fes Route ImouzzerBP 2427 Fes Morocco Univ Chouaib Doukkali Fac Sci El Jadida El Jadida 24000 Morocco United Arab Emirates Univ Coll Engn Architectural Engn Dept POB 15551 Al Ain U Arab Emirates

Among CSP technologies, the linear Fresnel reflector (LFR) can provide reliable carbon-neutral electricity for large-scale applications. In this study, the performance of a large solar LFR power plant under varying climatic conditions and the dependency of the performance on major plant design specifications, such as solar multiple and full-load thermal storage hours, were examined. Next, artificial neural network (ANN) surrogate models were introduced to predict the annual capacity factor of 100 MWe power plants operating with LFR technology. Single-hidden-layer ANN models with different numbers of neurons in the hidden layer were used and the Levenberg-Marquardt training algorithm was adopted. To overcome overfitting, validation and Bayesian Regularization approaches were compared. As training and testing data, 36 geographical sites with various combinations of design parameters were used. Through multi-objective optimization techniques, including the Multi- Objective Particle-Swarm Optimizer and Multi-Objective Grey Wolf Optimizer coupled with ANN surrogate modeling, this study navigates the trade-offs to identify Pareto-optimal solutions for large-scale LFR-based CSP integration based on the energy and cost criteria. The study also identified Site 4 (S4) as a promising candidate for optimal balance between the capacity factor (51.05%) and specific cost (5246.71$/kW), showcasing the practical implications of the research for sustainable and efficient CSP plant implementation.

关键词： Artificial neural network Capacity factor Linear fresnel reflector Multi-objective optimization training algorithm Metaheuristics

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：