检索结果-内蒙古大学图书馆

DIAGNOSING DYNAMIC FAULTS USING MODULAR NEURAL NETS

IEEE EXPERT-INTELLIGENT SYSTEMS & THEIR APPLICATIONS 1993年第2期8卷 44-53页

作者： LEONARD, JA KRAMER, MA MIT DEPT CHEM ENGNCAMBRIDGEMA 02139

The use of radial basis function networks (RBFNs) for diagnosis and classification is discussed. Even though RBFNs can be trained quickly compared to backpropagation networks, the training effort is still significant for large-scale diagnosis problems. Rho-Net, an architecture that decomposes the dynamic classification problem in two ways, making such training tractable, is presented. The first decomposition reduces the amount of training data needed for any stage of the training process by constructing separate networks for each fault class. The second decomposition reduces the dimensionality of the input space by incorporating temporal information at the output of the network, instead of as a temporal window at the input of the net. Application of Rho-Nets to chemical process simulation is discussed.

关键词： Neural networks Testing Radial basis function networks Gaussian processes Extrapolation backpropagation algorithms Organizing Feature extraction Supervised learning Large-scale systems

来源：评论

学校读者我要写书评

暂无评论

Smart Proxy Modeling of a Fractured Reservoir Model for Production Optimization: Implementation of Metaheuristic Algorithm and Probabilistic Application

引用

NATURAL RESOURCES RESEARCH 2021年第3期30卷 2431-2462页

作者： Ng, Cuthbert Shang Wui Jahanbani Ghahfarokhi, Ashkan Nait Amar, Menad Torsaeter, Ole Norwegian Univ Sci & Technol Dept Geosci & Petr Trondheim Norway Dept Etud Thermodynam Div Labs Sonatrach Boumerdes Algeria

Numerical reservoir simulation has been recognized as one of the most frequently used aids in reservoir management. Despite having high calculability performance, it presents an acute shortcoming, namely the long computational time induced by the complexities of reservoir models. This situation applies aptly in the modeling of fractured reservoirs because these reservoirs are strongly heterogeneous. Therefore, the domains of artificial intelligence and machine learning (ML) were used to alleviate this computational challenge by creating a new class of reservoir modeling, namely smart proxy modeling (SPM). SPM is a ML approach that requires a spatio-temporal database extracted from the numerical simulation to be built. In this study, we demonstrate the procedures of SPM based on a synthetic fractured reservoir model, which is a representation of dual-porosity dual-permeability model. The applied ML technique for SPM is artificial neural network. We then present the application of the smart proxies in production optimization to illustrate its practicality. Apart from applying the backpropagation algorithms, we implemented particle swarm optimization (PSO), which is one of the metaheuristic algorithms, to build the SPM. We also propose an additional procedure in SPM by integrating the probabilistic application to examine the overall performance of the smart proxies. In this work, we inferred that the PSO had a higher chance to improve the reliability of smart proxies with excellent training results and predictive performance compared with the considered backpropagation approaches.

关键词： Reservoir simulation Dual-porosity dual-permeability Smart proxy modeling backpropagation algorithms Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Training partially recurrent neural networks using evolutionary strategies

引用

IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING 1997年第2期5卷 192-194页

作者： Greenwood, GW Dept. of Electr. & Comput. Sci. Western Michigan Univ. Kalamazoo MI USA

This correspondence presents the latest results of using evolutionary strategies (ES's) to design partially recurrent neural networks for viseme recognition. ES's are stochastic optimization algorithms based upon the principles of natural selection found in the biological world. Our results indicate that ES's can be effectively used to determine the synaptic weights in neural networks and can outperform backpropagation techniques.

关键词： Recurrent neural networks Speech recognition Lips Pipeline processing Telephony Auditory system Stochastic processes backpropagation algorithms Neural networks

来源：评论

学校读者我要写书评

暂无评论

AN ANALYSIS OF COARSE-GRAIN PARALLEL TRAINING OF A NEURAL-NET

引用

NETWORK-COMPUTATION IN NEURAL SYSTEMS 1995年第1期6卷 73-91页

作者： COETZEE, L BOTHA, EC Department of Electrical and Electronic Engineering University of Pretoria Pretoria 0002 South Africa

In modern day pattern recognition, neural nets are used extensively. General use of a feedforward neural net consists of a training phase followed by a classification phase. Classification of an unknown test vector is very fast and only consists of the propagation of the test vector through the neural net. Training involves an optimization procedure and is very time consuming since a feasible local minimum is sought in weight space. If the training algorithm is based on error backpropagation the optimization procedure consists of the following steps: computation of the activation of the net when all the training examples are presented to it;computation of an error function based on the activation;computation of the gradients at a point in weight space;and finally, the adaptation of the weight values of the net. In this paper we present an analysis of a parallel implementation of the backpropagation algorithm using conjugate-gradient optimization for a three-layered, feedforward neural network, using networked workstations as a virtual parallel machine. The instance of the virtual machine is the PVM system, developed at Oak Ridge National Laboratory. We compare the overall performance of the parallel machine with averaged sequential runs in a typical research environment. From this, we identify the general requirements such as the size of the data set and neural net which render the parallel implementation useful, compared with the sequential execution of the same neural net training procedure.

关键词： Networks Optimization Procedure Parallel Lines OAK RIDGE NATIONAL LABORATORY Neural network ERROR FUNCTIONS learning (artificial intelligence) backpropagation algorithms sequential carry test vectors Dataset Network

来源：评论

学校读者我要写书评

暂无评论

ERROR SURFACES FOR MULTILAYER PERCEPTRONS

引用

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS 1992年第5期22卷 1152-1161页

作者： HUSH, DR HORNE, B SALAS, JM Department of Electrical Engineering and Computer Engineering University of New Mexico Albuquerque NM USA

The paper explores the characteristics of error surfaces for the multilayer perceptron neural network. These characteristics help explain why learning techniques that use hill climbing methods are so slow in these networks. They also help provide insights into techniques that may help speed learning. Several important characteristics are revealed. First, the surface has a stair-step appearance with many very flat and very steep regions. In fact, when the number of training samples is small there is often a one-to-one correspondence between individual training samples and the steps on the surface. As the number of training samples is increased the surface becomes smoother. In addition the surface has flat regions that extend to infinity in all directions making it dangerous to apply learning algorithms that perform line searches. The magnitude of gradients on the surface is found to span several orders of magnitude, strongly supporting the need for floating point representations during learning. The consequences of various weight initialization techniques are also discussed.

关键词： Multilayer perceptrons Neural networks Multi-layer neural network Convergence backpropagation algorithms Logic Fuzzy set theory H infinity control Information processing Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Exploring and comparing the best ''direct methods'' for the efficient training of MLP-networks

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1996年第6期7卷 1497-1502页

作者： DiMartino, M Fanelli, S Protasi, M Dipartimento di Matematica University di Roma Tor Vergata Rome Italy

It is well known that the main difficulties of the algorithms based on backpropagation are the susceptibility to local minima and the slow adaptivity to the patterns during the training. In this paper, we present a class of algorithms, which overcome the above difficulties by utilizing some ''direct'' numerical methods for the computation of the matrices of weights. In particular, we investigate the performances of the algorithms FBFBK-LSB (the first part named for the authors' initials and the second meaning least-squares backpropagation) and iterative conjugate gradient singular-value decomposition (ICGSVD), respectively, introduced by Barmann and Biegler-Konig and by the authors. Numerical results on Several benchmark problems show a major reliability and/or efficiency of our algorithm ICGSVD.

关键词： Benchmark testing Direct Method minimum algorithms Numerical methods backpropagation algorithms back propagation conjugate gradient

来源：评论

学校读者我要写书评

暂无评论

Neural network models for a resource allocation problem

引用

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS 1998年第2期28卷 276-284页

作者： Walczak, S Univ S Alabama Sch Comp & Informat Sci Mobile AL 36688 USA

University admissions and business personnel offices use a limited number of resources to process an ever-increasing quality of student and employment applications. Application systems are further constrained to identify and acquire, in a limited time period,those candidates who are most likely to accept an offer of enrollment or employment. Neural networks are a blew methodology;to this particular domain. Various neural network architectures and learning algorithms are analyzed comparatively to determine the applicability of supervised learning neural networks to the domain problem of personnel resource allocation and to identify optimal learning strategies in this domain. This paper Focuses on multilayer perceptron backpropagation, radial basis function, counterpropagation, general regression, fuzzy ARTMAP, and linear vector quantization neural networks. Each neural network predicts the probability of enrollment and nonenrollment for individual student applicants. backpropagation networks produced the best overall performance. Network performance results are measured by the reduction in the counselor's student case load and corresponding increases in student enrollment. The backpropagation neural networks achieve a 56% reduction in counselor case load.

关键词： Neural networks Resource management Personnel Employment backpropagation algorithms Algorithm design and analysis Supervised learning Multilayer perceptrons Fuzzy neural networks Vector quantization

来源：评论

学校读者我要写书评

暂无评论

A RECURRENT NEWTON ALGORITHM AND ITS CONVERGENCE PROPERTIES

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第3期6卷 779-783页

作者： KUAN, CM Department of Economics National Taiwan University Taipei Taiwan

In this paper a recurrent Newton algorithm for an important class of recurrent neural networks is introduced. It is noted that a suitable constraint must be imposed on recurrent variables to ensure proper convergence behavior. The simulation results show that the proposed Newton algorithm with the suggested constraint perform uniformly better than the back-propagation algorithm and the Newton algorithm without the constraint, in terms of mean-squared errors.

关键词： Convergence Signal processing algorithms backpropagation algorithms Output feedback Recurrent neural networks Target recognition Neural networks Feedforward neural networks Process control System identification

来源：评论

学校读者我要写书评

暂无评论

Non-linear system modeling using LSTM neural networks

引用

IFAC-PapersOnLine 2018年第13期51卷 485-489页

作者： Gonzalez, Jesús Yu, Wen Mexico City Mexico

Long-Short Term Memory (LSTM) is a type of Recurrent Neural Networks (RNN). It takes sequences of information and uses recurrent mechanisms and gate techniques. LSTM has many advantages over other feedforward and recurrent NNs in modeling of time series, such as audio and video. However, in non-linear system modeling normal LSTM does not work well(Wang, 2017). In this paper, we combine LSTM with NN, and use the advantages. The novel neural model consists of hierarchical recurrent networks and one multilayer perceptron. We design a special learning algorithm which uses backpropagation, and backpropagation through time methods. We use two non-linear system examples to compare our neural modeling with other well known methods. The results show that for the simulation model (only the test input is used and the past test output is not used), the modified LSTM model proposed in this paper is much better than the other existing neural models. © 2018

关键词： Long short-term memory backpropagation algorithms Linear systems Multilayer neural networks Neural networks Nonlinear systems Audio and video Back propagation through time Black box identification LSTM Nonlinear system modeling Recurrent networks Recurrent neural network (RNN) Simulation model

来源：评论

学校读者我要写书评

暂无评论

Monthly Energy Consumption Forecasting Based on Windowed Momentum Neural Network

引用

IFAC-PapersOnLine 2015年第30期48卷 433-438页

作者： Mishra, Sukumar Singh, Vivek Kumar Electrical Engineering Department Indian Institute of Technology Delhi New Delhi110016 India

Artificial Neural Network (ANN) with adaptability and non-linearity is well suited to perform forecasting tasks. The paper proposes the systematic approach of monthly energy forecasting using Windowed Momentum Algorithm in ANN. It describes the mathematical foundations and implementation to calculate the monthly energy demand using previous three years consecutive monthly energy data and weather information. The results are compared with the standard momentum, generally used in Back Propagation Algorithm. The proposed algorithm shows good accuracy with maximum mean absolute percentage error of 1.177%. © 2015, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： Forecasting backpropagation algorithms Energy utilization Momentum Neural networks Energy data Energy demands Energy forecasting Mathematical foundations Mean absolute percentage error Weather information

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：