检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： M.E. Rimer T.L. Andersen T.R. Martinez Computer Science Department Brigham Young University Provo UT USA

ISBN: (纸本)0780370449

Artificial neural networks provide an effective empirical predictive model for pattern classification. However, using complex neural networks to learn very large training sets is often problematic, imposing prohibitive time constraints on the training process. We present four practical methods for dramatically decreasing training time through dynamic stochastic sample presentation, a technique we call speed training. These methods are shown to be robust to retaining generalization accuracy over a diverse collection of real world data sets. In particular, the stochastic presentation with error threshold technique achieves a training speedup of 4278% on a large OCR database with no detectable loss in generalization.

关键词： Stochastic processes Training data Neural networks Testing Robustness backpropagation algorithms Convergence Computer science Predictive models Time factors

来源：评论

学校读者我要写书评

暂无评论

Adaptive error-constrained backpropagation algorithm

Adaptive error-constrained backpropagation algorithm

引用

IEEE Workshop on Neural Networks for Signal Processing

作者： Sooyong Choi KyunByoung Ko Daesik Hong Department of Electrical and Computer Engineering Yonsei University Seoul South Korea

ISBN: (纸本)0780371968

In order to accelerate the convergence speed of the conventional BP algorithm, constrained optimization techniques are applied to the BP algorithm. First, the noise-constrained least mean square algorithm and the zero noise-constrained LMS algorithm are applied (designated the NCBP and ZNCBP algorithms, respectively). These methods involve an important assumption: the filter or the receiver in the NCBP algorithm must know the noise variance. By means of extention and generalization of these algorithms, the authors derive an adaptive error-constrained BP algorithm and its simplified algorithm, in which the error variance is estimated. This is achieved by modifying the error function of the conventional BP algorithm using Lagrangian multipliers. The convergence speeds of the proposed algorithms are 20 to 30 times faster than those of the conventional BP algorithm, and are faster than or almost the same as that achieved with a conventional linear adaptive filter using an LMS algorithm.

关键词： backpropagation algorithms Signal processing algorithms Neural networks Convergence Acceleration Lagrangian functions Least squares approximation Filters Additive noise Gaussian noise

来源：评论

学校读者我要写书评

暂无评论

A backpropagation learning framework for feedforward neural networks

A backpropagation learning framework for feedforward neural ...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： X. Yu M. Onder Efe O. Kaynak Faculty of Informatics and Communication Central Queensland University Rockhampton QLD Australia Department of Electrical and Electronic Engineering Bogazici University Istanbul Turkey

ISBN: (纸本)0780366859

In this paper, a general backpropagation learning framework for the training of feedforward neural networks is proposed. The convergence to global minimum under the framework is investigated using the Lyapunov stability theory. It is shown the existing feedforward neural network training algorithms are special cases of the proposed framework.

关键词： Neural networks Feedforward neural networks Lyapunov method Convergence Informatics backpropagation algorithms Function approximation Predictive models Data mining Neurons

来源：评论

学校读者我要写书评

暂无评论

backpropagation through time for a general class of recurrent network

Backpropagation through time for a general class of recurren...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： O. De Jeses M.T. Hagan Sch. of Electr. & Comput. Eng. Oklahoma State Univ. Stillwater OK USA School of Electrical and Computer Engineering Oklahoma State University Stillwater OK USA School of Electrical and Computer Engineering Oklahoma State University Stillwater OK

This paper introduces a general class of dynamic network, the layered digital dynamic network. It then derives the backpropagation-through-time algorithm for computing the gradient of the network error with respect to... 详细信息

ISBN: (纸本)0780370449

关键词： backpropagation algorithms Computer networks Computer errors Neural networks Output feedback Neurofeedback Computer architecture Feedback loop Perturbation methods Equations

来源：评论

学校读者我要写书评

暂无评论

A parallel implementation of the batch backpropagation training of neural networks

A parallel implementation of the batch backpropagation train...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： A. Novokhodko S. Valentine Electrical and Computer Engineering Department University of Missouri Rolla Rolla MO USA

ISBN: (纸本)0780370449

Neural networks, being naturally parallel, inspire researchers to seek efficient implementations for various parallel architectures. However, the vast fine-grain parallelism of many tightly connected simple nodes poses a problem for traditional parallel computing on a small number of powerful processors. One approach is to parallelize not the neural network itself, but the process of its training, which is the most numerically intensive part in neural network computing. During the batch training each input pattern/signal is presented to the neural network, a response is obtained and evaluated, and a direction of network parameters change (the cost function gradient) is calculated using the backpropagation algorithm. The goal is obtained parallelizing MATLAB's matrix multiplication routine. The message passing interface is used for the parallel implementation. The implementation allows to parallelize generally non-parallel procedures offered by MATLAB.

关键词： Neural networks Parallel processing Parallel architectures Computer networks Concurrent computing Cost function backpropagation algorithms Computer languages Message passing MATLAB

来源：评论

学校读者我要写书评

暂无评论

Meta-learning with backpropagation

Meta-learning with backpropagation

引用

International Joint Conference on Neural Networks (IJCNN)

作者： A.S. Younger S. Hochreiter P.R. Conwell Computer Science University of Colorado Boulder CO USA Physics Department Westminster College Salt Lake UT USA

ISBN: (纸本)0780370449

Introduces gradient descent methods applied to meta-learning (learning how to learn) in neural networks. Meta-learning has been of interest in the machine learning field for decades because of its appealing applications to intelligent agents, non-stationary time series, autonomous robots, and improved learning algorithms. Many previous neural network-based approaches toward meta-learning have been based on evolutionary methods. We show how to use gradient descent for meta-learning in recurrent neural networks. Based on previous work on fixed-weight learning neural networks, we hypothesize that any recurrent network topology and its corresponding learning algorithm(s) is a potential meta-learning system. We tested several recurrent neural network topologies and their corresponding forms of backpropagation for their ability to meta-learn. One of our systems, based on the long short-term memory neural network developed a learning algorithm that could learn any two-dimensional quadratic function (from a set of such functions) after only 30 training examples.

关键词： Neural networks USA Councils Recurrent neural networks backpropagation algorithms Computer science Network topology Educational institutions Physics Cities and towns Robots

来源：评论

学校读者我要写书评

暂无评论

Complex backpropagation neural network using elementary transcendental activation functions

Complex backpropagation neural network using elementary tran...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： T. Kim T. Adali Department of Computer Science and Electrical Engineering University of Maryland Baltimore County Baltimore MD USA MITRE Corporation McLean VA USA

Designing a neural network (NN) for processing complex signals is a challenging task due to the lack of bounded and differentiable nonlinear activation functions in the entire complex domain C. To avoid this difficulty, 'splitting', i.e., using uncoupled real sigmoidal functions for the real and imaginary components has been the traditional approach, and a number of fully complex activation functions introduced can only correct for magnitude distortion but can not handle phase distortion. We have previously introduced a fully complex NN that uses a hyperbolic tangent function defined in the entire complex domain and showed that for most practical signal processing problems, it is sufficient to have an activation function that is bounded and differentiable almost everywhere in the complex domain. In this paper, the fully complex NN design is extended to employ other complex activation functions of the hyperbolic, circular, and their inverse function family. They are shown to successfully restore the nonlinear amplitude and phase distortions of non-constant modulus modulated signals.

关键词： Neural networks Signal processing Phase distortion backpropagation algorithms Nonlinear distortion Signal restoration Phase modulation Least squares approximation Quadrature phase shift keying Equations

来源：评论

学校读者我要写书评

暂无评论

A normalised backpropagation learning algorithm for multilayer feed-forward neural adaptive filters

A normalised backpropagation learning algorithm for multilay...

引用

IEEE Workshop on Neural Networks for Signal Processing

作者： A.I. Hanna D.P. Mandic M. Razaz School of Information Systems University of East Anglia Norwich UK

Analysis of a normalised backpropagation (NBP) algorithm employed in feed-forward multilayer nonlinear adaptive filters trained by backpropagation is provided. It is first shown that a degree of freedom in training of a nonlinear adaptive filter can be removed according to the relationship between the gain of the activation function, learning rate and weight matrix. The derivation of the NBP algorithm for a multilayer feed-forward neural adaptive filter is then provided based upon the minimisation of the instantaneous output error of the filter. Simulation results show that the NBP algorithm converges faster than a standard backpropagation algorithm and achieves better prediction gain when applied to nonlinear and non-stationary signals.

关键词： backpropagation algorithms Nonhomogeneous media Feedforward systems Adaptive filters Character generation

来源：评论

学校读者我要写书评

暂无评论

Neural Network Based Fault Detection in Hydroponics

引用

IFAC Proceedings Volumes 2001年第26期34卷 37-42页

作者： K.P. Ferentinos L.D. Albright B. Selman Department of Agricultural and Biological Engineering Cornell University Ithaca NY 14853 USA Department of Computer Science Cornell University Ithaca NY 14853 USA.

A fault detection model for hydroponic systems, based on the feedforward Neural Network methodology was developed. Three kinds of faults were considered: mechanical, sensor and biological faults. In this paper, a preliminary detection system is presented, which generally detects the existence of any faulty situations. In the developed network, only the two first kinds of faults were considered. Biological faults, because of their particularities, were treated separately and some of their characteristics are presented at the end.

关键词： Neural Networks Fault Detection Hydroponics backpropagation algorithms

来源：评论

学校读者我要写书评

暂无评论

H/sub /spl infin//-learning of layered neural networks

引用

IEEE Transactions on Neural Networks 2001年第6期12卷 1265-1277页

作者： K. Nishiyama K. Suzuki Department of Computer and Information Science Faculty of Engineering Iwate University Morioka Japan

Although the backpropagation (BP) scheme is widely used as a learning algorithm for multilayered neural networks, the learning speed of the BP algorithm to obtain acceptable errors is unsatisfactory in spite of some improvements such as introduction of a momentum factor and an adaptive learning rate in the weight adjustment. To solve this problem, a fast learning algorithm based on the extended Kalman filter (EKF) is presented and fortunately its computational complexity has been reduced by some simplifications. In general, however, the Kalman filtering algorithm is well known to be sensitive to the nature of noises which is generally assumed to be Gaussian. In addition, the H/sub /spl infin// theory suggests that the maximum energy gain of the Kalman algorithm from disturbances to the estimation error has no upper bound. Therefore, the EKF-based learning algorithms should be improved to enhance the robustness to variations in the initial values of link weights and thresholds as well as to the nature of noises. The paper proposes H/sub /spl infin//-learning as a novel learning rule and to derive new globally and locally optimized learning algorithms based on H/sub /spl infin//-learning. Their learning behavior is analyzed from various points of view using computer simulations. The derived algorithms are also compared, in performance and computational cost, with the conventional BP and EKF learning algorithms.

关键词： backpropagation algorithms Kalman filters Neural networks Multi-layer neural network Computational complexity Filtering algorithms Gaussian noise Estimation error Upper bound Noise robustness

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：