检索结果-内蒙古大学图书馆

Why neural networks apply to scientific computing?

Theoretical & Applied Mechanics Letters 2021年第3期11卷 125-129页

作者： Shaoqiang Tang Yang Yang HEDPS and LTCS College of EngineeringPeking UniversityBeijing 100871China

In recent years,neural networks have become an increasingly powerful tool in scientific *** universal approximation theorem asserts that a neural network may be constructed to approximate any given continuous function at desired *** backpropagation algorithm further allows efficient optimization of the parameters in training a neural *** by GPU’s,effective computations for scientific and engineering problems are thereby *** addition,we show that finite element shape functions may also be approximated by neural networks.

关键词： Neural networks Universal approximation theorem backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Modified Nonlinear Neural Network Forecasting Models on Malaysian Sand Costs Indices

Modified Nonlinear Neural Network Forecasting Models on Mala...

引用

IEEE Symposium on Computer Applications and Industrial Electronics (ISCAIE)

作者： Kamaruddin, Saadi Bin Ahmad Ghani, Nor Azura Md Ramli, Norazan Mohamed Int Islamic Univ Computat & Theoret Sci Dept Kuala Lumpur Malaysia Univ Teknol MARA Fac Comp & Math Sci Ctr Stat & Decis Sci Studies Shah Alam 40450 Selangor Darul Malaysia

ISBN: (纸本)9781479989690

Artificial Neural Networks (ANNs) have been adapted actively in the time series-prediction arena, but the presence of outliers that usually occur in the time series data may pollute the network training data. This is due to its ability to automatically learn any pattern without prior assumptions as well as loss of generality. In theory, the most common algorithm for training the network is the backpropagation (BP) algorithm which leans on the minimization of the ordinary least squares (OLS) estimator or more specifically, the mean squared error (MSE). Nonetheless, this algorithm is not entirely robust when the outliers are present, and it may lead to false prediction of future values. Therefore, in this current study, we present a new algorithm which manipulates the particle swarm optimization on the least median of squares (PSO-LMedS) estimator for artificial neural network nonlinear autoregressive moving average (ANN-NARMA) model to cater for the outlying issue in time series data. Additionally, the performance of the consolidated model with comparison with the other robust ANN-NARMA models using M-estimators, Iterative LMedS and Particle Swarm Optimization on LMedS with respect to mean squared error (MSE), mean absolute deviation (MAD), root mean squared error (RMSE), mean absolute percentage error (MAPE) and Rsquared values are also highlighted in this paper. Meanwhile, the real-industrial monthly data of Malaysian Sand price index from January 1980 to December 2012 (base year 1980=100) were used. It was found that the robustified ANN-NARMA model using Least Median Square with Particle Swarm Optimization produced the best result with R-squared values equal to 100 in all training, testing and validation sets. It is expected that the findings would assist the respected authorities involve in PFI construction projects to overcome cost overruns.

关键词： ANN time series backpropagation algorithm nonlinear autoregressive robust estimators

来源：评论

学校读者我要写书评

暂无评论

Exploring the non-linearity in empirical modelling of a steel system using statistical and neural network models

Exploring the non-linearity in empirical modelling of a stee...

引用

3rd International Conference on Modeling and Analysis of Semiconductor Manufacturing (MASM 2005)

作者： Das, Prasun Datta, Shubhabrata Indian Stat Inst SQC & OR Unit Kolkata 700108 India Bengal Engn & Sci Univ Sch Mat Sci & Engn Sibpur 711103 Howrah India

The relationship between the physical properties of metal is often very complex in nature with its chemistry and several other rolling parameters in operation. Non-linear regression models play a very important role in modelling the underlying mechanism, provided it is known. Artificial neural networks provide a wide class of general-purpose and flexible non-linear regression models. The most commonly used neural networks, called multi-layered perceptrons, can vary the complexity of the model from a simple parametric model to a highly flexible nonparametric model. In this particular work, an industry-based data set is used for learning and optimizing the neural network architecture using some well-known algorithms for prediction under neural-net systems. The outcome of the analysis is compared with the results achieved through empirical statistical modelling from its prediction error level and the knowledge of materials science.

关键词： artificial neural network steel regression models learning backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Bayesian Regularization and Levenberg-Marquardt Training algorithm for Localization in Wireless Sensor Network

Comparative Analysis of Bayesian Regularization and Levenber...

引用

15th International Conference on Advanced Communications Technology (ICACT)

作者： Payal, Ashish Rai, C. S. Reddy, B. V. R. GGS Indraprastha Univ Univ Sch Informat & Commun Technol New Delhi India

ISBN: (纸本)9788996865018;9781467331487

Wireless sensor networks (WSNs) have many applications in the field of disaster management, military, healthcare and environmental monitoring. Capability of WSNs is further enhanced by the efficient localization algorithms. Localization is the process by which a sensor node determines its own location after deployment. Neural approaches are gaining popularity in evolving new localization algorithms that are capable of optimizing various parameters of WSNs. In this paper, we analyse two backpropagation algorithms based on multi-layer Perceptron (MLP) neural network. The network is trained using static sensor nodes placed in a grid with their coordinates known. The input values are distances from each anchor nodes to a particular sensor node. The output is the actual coordinates of the sensor nodes. After training, the network will be able to predict the coordinates of unknown sensor nodes. This MLP model is analyzed for Bayesian regularization and Levenberg-Marquardt training algorithm. Both algorithms are tested for the robustness and cross-validation. The simulation results demonstrate the effectiveness of the proposed model on localization error.

关键词： Localization Wireless Sensor Network backpropagation algorithm Neural network Bayesian regularization

来源：评论

学校读者我要写书评

暂无评论

Predicting Students Yearly Performance using Neural Network: A Case Study of BSMRSTU 5

Predicting Students Yearly Performance using Neural Network:...

引用

5th International Conference on Informatics, Electronics and Vision (ICIEV)

作者： Sikder, Md. Fahim Uddin, Md. Jamal Halder, Sajal Bangabandhu Sheikh Mujibur Rahman Sci & Technol U Dept Comp Sci & Engn Dhaka Bangladesh

ISBN: (纸本)9781509012695

Students academic performance is the reflection of both academic background and family support. This performance record is critical for the educational institution because they can learn from this to improve their quality. Educational data mining helps to analyze these data and extract information from it. We can determine the status of learners academic performance. For achieving this we can use techniques like decision tree, neural network, classification, data clustering, support vector machine and so on. In this paper, we will predict student's yearly performance in the form of Cumulative Grade Point Average (CGPA) using neural network and compare that with real CGPA. In this regard, a real dataset would be of great importance. We used real dataset from Bangabandhu Sheikh Mujibur Rahman Science and Technology University (BSMRSTU) to perform the prediction.

关键词： Neural Network Prediction backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Use of an artificial neural network to predict population dynamics of the forest-pest pine needle gall midge (Diptera: Cecidomyiida)

引用

ENVIRONMENTAL ENTOMOLOGY 2000年第6期29卷 1208-1215页

作者： Chon, TS Park, YS Kim, JM Lee, BY Chung, YJ Kim, Y Pusan Natl Univ Dept Biol Pusan 609735 South Korea

The backpropagation algorithm in artificial neural networks was used to forecast dynamic data of a forest pest population of the pine needle gall midge, Thecodiplosis japonensis Uchida et Inouye, a serious pest in pine trees in northeast Asia. Data for changes in population density were sequentially given as input, whereas densities of subsequent samplings were provided as matching target data for training of the network. Convergence was reached, generally after 20,000 iterations with learning coefficients of 0.5-0.8. When new input data were given to the trained network, recognition was possible and population density at the subsequent sampling time could be predicted.

关键词： Thecodiplosis japonensis pine needle gall midge population dynamics prediction artificial neural network backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

ARTIFICIAL NEURAL NETWORKS LEARNING IN ROC SPACE

ARTIFICIAL NEURAL NETWORKS LEARNING IN ROC SPACE

引用

1st International Joint Conference on Computational Intelligence

作者： Castro, Cristiano Leite Braga, Antonio Padua Univ Fed Lavras Dept Comp Sci Campus UnivCaixa Postal 3037 BR-37200000 Lavras Brazil Univ Fed Minas Gerais Dept Elect Engn BR-30161970 Belo Horizonte MG Brazil

ISBN: (纸本)9789896740146

In order to control the trade-off between sensitivity and specificity of MLP binary classifiers, we extended the backpropagation algorithm, in batch mode, to incorporate different misclassification costs via separation of the global mean squared error between positive and negative classes. By achieving different solutions in ROC space, our algorithm improved the MLP classifier performance on imbalanced training sets. In our experiments, standard MLP and SVM algorithms were compared to our solution using real world imbalanced applications. The results demonstrated the efficiency of our approach to increase the number of correct positive classifications and improve the balance between sensitivity and specificity.

关键词： Multi-Layer Perceptron (MLP) backpropagation algorithm ROC analysis Imbalanced data sets Cost-sensitive learning

来源：评论

学校读者我要写书评

暂无评论

A New Training Method For Solving The XOR Problem 5

A New Training Method For Solving The XOR Problem

引用

5th International Conference on Electrical Engineering - Boumerdes (ICEE-B)

作者： Ladjouzi, Samir Grouni, Said Kirat, Abderrahmen Soufi, Youcef Univ Bouira Dept Elect Engn Bouira Algeria Univ Boumerdes Dept Ind Maintenance Boumerdes Algeria Univ Tebessa Dept Elect Engn Tebessa Algeria

ISBN: (纸本)9781538606865

Training of Artificial Neural Networks (ANN) is an important step to make the network able to accomplish the desired task. This capacity of learning in such networks makes them applied in many applications as modeling and control. However, many of training algorithms have some drawbacks like: too many parameters to be estimated, important calculus time. In this paper, we propose a very simple method to train a Single Hidden Layer Perceptron (SHLP) based on replacing the traditional ANN's phase training by another approach called Neural Least Mean Square (NLMS) problem resolution. The key of this method is to compute some ANN's weights by the Least Mean Square (LMS) formula, and to leave others weights to their initial values. This new training method is applied to the classical XOR problem and the results are compared with the conventional backpropagation algorithm. The obtained results were satisfactory and the comparison made with the classical algorithm revealed that our method allowed to reduce several parameters in the learning, namely: the computation time, the overall value of the error squared, the number of iterations and the number of weights to be adjusted.

关键词： ANN's phase training Single Hidden Layer Perceptron (SHLP) Neural Least Mean Square (NLMS) XOR problem backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Network with Hyperbolic Tangent Activation Function to Improve the Accuracy of COCOMO II Model 2nd

引用

2nd International Conference on Soft Computing and Data Mining (SCDM)

作者： Alshalif, Sarah Abdulkarem Ibrahim, Noraini Herawan, Tutut Univ Tun Hussein Onn Malaysia Parit Raja 86400 Johor Malaysia Univ Malaya Kuala Lumpur 50603 Malaysia

ISBN: (纸本)9783319512815;9783319512792

In software engineering, Constructive Cost Model II (COCOMO II) is one of the most cited, famous and widely used model to estimate and predict some important features of the software project such as effort, cost, time and manpower estimations. Lately, researchers incorporate it with soft computing techniques to solve and reduce the ambiguity and uncertainty of its software attributes. In this paper, Artificial Neural Network (ANN) with Hyperbolic Tangent Activation Function is used to improve the accuracy of the COCOMO II model and the backpropagation learning algorithm used in the training process. In the experiment, COCOMO II SDR dataset is used for training and testing the model. The result shows that eight out of twelve projects have a closer effort value of actual effort. It shows that the proposed model produces better performance comparing to sigmodal function.

关键词： Software cost estimation COCOMO II Artificial neural network Hyperbolic tangent activation function backpropagation algorithm

来源：评论

学校读者我要写书评

暂无评论

Neurofuzzy Inference System for Diagnosis of Leukemia

Neurofuzzy Inference System for Diagnosis of Leukemia

引用

International Conference on Innovative Applications of Computational Intelligence on Power Energy and Controls with their Impact on Humanity (CIPECH)

作者： Ekata Tyagi, Praveen Kumar Singhal, Harshit KIET Dept Math Ghaziabad India KIET Dept Elect & Elect Engn Ghaziabad India

ISBN: (纸本)9781479958726

In this paper, we are using Neurofuzzy system for either prediagnosis or preidentification of leukemia. Mainly the technique of backpropagation algorithm is used in order to complete the process of training and testing our data, that (data) has already been obtained by generating the Sugeno based model of all considered rules, based on different symptoms of Leukemia taken as input in this procedure. In carcinogenesis, Neurofuzzy is favourably applicable to sort out various types of problems occurs in both pre-clinical as well as post-clinical types of diagnosis. In this application, a fuzzy logic dependent system is presented for the support of the justification of disease for prediagnosis of Leukemia.

关键词： backpropagation algorithm leukemia Neurofuzzy inference system

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：