检索结果-内蒙古大学图书馆

International Conference on Neural Networks

作者： C.S. Herrmann F. Reine Technische Hochschule Darmstadt Fachgebiet Intellektik Darmstadt Germany Technische Hochschule Darmstadt Institut für Datentechnik Darmstadt Germany

We propose a new learning strategy to consider aspects of cognitive adequacy during the training of artificial neural networks instead of merely taking the overall error into account. Well known learning algorithms for neural networks can be adapted in a way that leads to an adequate behaviour by using a fuzzy system to provide pattern specific learning rates based on a predetermined measure of pattern difficulty and the current classification error. First experiments with adequate backpropagation show that adequate learning provides faster generalization-error convergence than its conventional counterpart.

关键词： Neural networks Humans Artificial intelligence Artificial neural networks Psychology backpropagation algorithms Fuzzy systems Current measurement Convergence Biological system modeling

来源：评论

学校读者我要写书评

暂无评论

Functional site prediction on the DNA sequence by artificial neural networks

Functional site prediction on the DNA sequence by artificial...

引用

IEEE International Joint Symposia on Intelligence and Systems

作者： A. Hatzigeorgiou N. Mache M. Reczko Biol. Structure & BioComputer Progr European Molecular Biology Laboratory Heidelberg Germany IPVS Universität Stuttgart Stuttgart Germany Synaptic Limited Greece

A modular system of neural networks is used to identify genes in DNA sequences of eukaryotic organisms. The identification task is decomposed into the detection of distinct signals using separate neural network modules. Such signals are coding regions, splice sites and transcription start regions (cap-site). A focus of the work is the use of back-percolation, cascade correlation, and time-delay neural networks. These give, in this particular application, better generalization than the well known backpropagation algorithm. This system achieves a prediction accuracy comparable to the traditionally designed gene identification packages and is able to produce more accurate protein sequences from the constructed gene structures.

关键词： DNA Sequences Artificial neural networks Organisms Signal processing Signal detection Neural networks backpropagation algorithms Accuracy Packaging

来源：评论

学校读者我要写书评

暂无评论

Dynamic neural network control of nonlinear-time varying systems: stability analysis, optimal network structure, and on-line adaptation

Dynamic neural network control of nonlinear-time varying sys...

引用

Conference of the North American Fuzzy Information Processing Society - NAFIPS

作者： M. Nikravesh Earth Sciences Division of Lawrence Berkeley National Laboratory and Department of Materials Science and Mineral Engineering University of California Berkeley CA USA

In this paper, dynamic neural network control (DNNC) is presented as a control strategy which uses a neural network to model the process and then applies the mathematical inversion of the process model to design the controller. DNNC falls into the large class of model predictive controllers, many of which are now widely used in industry. The objectives of this paper are: to study the stability properties of DNNC; and to study the on-line adaptation properties of DNNC. In this study four basic assumptions are made. The process is modeled with continuous time functions. If the process is nonstationary, it is also necessary to assure that changes will be continuous and smooth over small intervals of time, i.e. that process parameters change in a continuous manner. The time between model adaptation is small relative to time scale of parameter changes. Process parameters will not change at once, but only a small subset of them.

关键词： Optimal control Nonlinear control systems Control systems Stability analysis Biological neural networks Predictive models Neural networks Mathematical model Process control backpropagation algorithms

来源：评论

学校读者我要写书评

暂无评论

Attentional Mode Neural Network: A New Approach For Real-time Self-learning

Attentional Mode Neural Network: A New Approach For Real-tim...

引用

IEEE International Symposium on Circuits and Systems (ISCAS)

作者： P.M. Engel Instituto de Informática Universidade Federal do Rio Grande do Sul-Brazil

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of a new cache replacement scheme using SPEC

Performance evaluation of a new cache replacement scheme usi...

引用

International Phoenix Conference on Computers and Communications (IPCCC)

作者： H. Khalid M.S. Obaidat Department of Electrical Engineering The City College City University of New York New York NY USA

Presents a new neural network-based algorithm called KORA (Khalid-Obaidat Replacement Algorithm), that uses a backpropagation neural network (BPNN) for the purpose of guiding the line/block replacement decisions in a cache. The KORA algorithm attempts to approximate the replacement decisions made by the optimal scheme (OPT). The key to our algorithm is to identify and subsequently discard the dead lines in cache memories. This allows our algorithm to provide better cache performance as compared to the conventional LRU (least recently used), MRU (most recently used) and FIFO (first-in, first-out) replacement policies. Extensive trace-driven simulations were performed for 30 different cache configurations using different SPEC (Standard Performance Evaluation Corp.) programs. Simulation results have shown that KORA can provide a substantial improvement in the miss ratio over the conventional algorithms. Our work opens up new dimensions for research in the development of new and improved page replacement schemes for virtual memory systems and disk caches.

关键词： Neural networks backpropagation algorithms Cache memory History High performance computing Costs Cities and towns Educational institutions Optimized production technology Performance evaluation

来源：评论

学校读者我要写书评

暂无评论

An adaptive and fully sparse training approach for multilayer perceptrons

An adaptive and fully sparse training approach for multilaye...

引用

International Conference on Neural Networks

作者： Fang Wang Q.J. Zhang Department of Electronics Carleton University Ottawa Canada

An adaptive and fully sparse backpropagation training approach is proposed in this paper. The technique speeds up training by combining a sparse optimization concept with neural network training. The sparse phenomenon due to neuron activation, which is inherent in neural networks, is exploited in both feedforward and backpropagation phases. A new computational algorithm with sparse pattern reuse and refreshment has been developed together with the adaptation procedure of a new set of parameters which regulate the sparse training process. The proposed training approach has been applied to speech recognition and circuit extraction problems and achieved significant speed-up of training.

关键词： Multilayer perceptrons Neurons Neural networks Jacobian matrices backpropagation algorithms Speech recognition Circuits Optimization methods Feedforward neural networks Gradient methods

来源：评论

学校读者我要写书评

暂无评论

backpropagation NETWORK AND ITS CONFIGURATION FOR BLOOD-VESSEL DETECTION IN ANGIOGRAMS

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第1期6卷 64-72页

作者： NEKOVEI, R SUN, Y UNIV RHODE ISL DEPT ELECT ENGN KINGSTON RI 02881 USA

A neural-network classifier for detecting vascular structures in angiograms was developed. The classifier consisted of a multilayer feed-forward network window in which the center pixel was classified using gray-scale information within the window. The network was trained by using the back-propagation algorithm with the momentum term. Based on this image segmentation problem, the effect of changing network configuration on the classification performance was also characterized. Factors including topology, rate parameters, training sample set, and initial weights were systematically analyzed. The training set consisted of 75 selected points from a 256 x 256 digitized cineangiogram. While different network topologies showed no significant effect on performance, both the learning process and the classification performance were sensitive to the rate parameters. The best result was obtained with a small learning rate (0.05) and a medium momentum rate (0.5). The three-layer (121-17-2) network was adequate for the problem and showed good generalization to the entire cineangiogram and other images including-direct video angiograms and digital subtraction angiograms. In a comparative study, the network demonstrated its superiority in classification performance;its classification accuracy was 92%, as compared to 68% from a maximum likelihood estimation method and 83% from a method based on iterative ternary classification. It was also shown that the trained neural-network classifier was equivalent to a generalized matched filter with a nonlinear decision tree.

关键词： Blood vessels Network topology Biomedical imaging Nonhomogeneous media Gray-scale backpropagation algorithms Image segmentation Classification tree analysis Matched filters Decision trees

来源：评论

学校读者我要写书评

暂无评论

DYNAMIC LEARNING RATE OPTIMIZATION OF THE backpropagation ALGORITHM

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第3期6卷 669-677页

作者： YU, XH CHEN, GA CHENG, SX Department of Radio Engineering National Communications Research Laboratory South-East University Nanjing China

It has been observed by many authors that the backpropagation (BP) error surfaces usually consist of a large amount of flat regions as well as extremely steep regions, As such, the BP algorithm with a fixed learning rate will be low efficient. This paper considers dynamic learning rate optimization of the BP algorithm using derivative information, An efficient method of deriving the first and second derivatives of the objective function with respect to the learning rate is explored, which does not involve explicit calculation of second-order derivatives in weight space, but rather uses the information gathered from the forward and backward propagation. Several learning rate optimization approaches are subsequently established based on linear expansion of the actual outputs and line searches with acceptable descent value and Newton-like method, respectively. Simultaneous determination of the optimal learning rate and momentum is also introduced by showing the equivalence between the momentum version BP and the conjugate gradient method. Since these approaches are constructed by simple manipulations of the obtained derivatives, the computational and storage burden scale with the network size exactly like the standard BP algorithm, and the convergence of the BP algorithm is accelerated within a remarkable reduction (typically by factor 10 to 50, depending upon network architectures and applications) in the running time for the overall learning process. Numerous computer simulation results are provided to support the present approaches.

关键词： backpropagation algorithms Computer networks Iterative algorithms Optimization methods Gradient methods Convergence Acceleration Computer architecture Application software Computer simulation

来源：评论

学校读者我要写书评

暂无评论

AN ADAPTIVE STEP-SIZE FOR backpropagation USING LINEAR LOWER BOUNDING FUNCTIONS

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 1995年第5期43卷 1243-1248页

作者： YU, M CHANG, TS Department of Electrical and Computer Engineering University of California Davis CA USA

An adaptive step size is presented for the backpropagation algorithm in feedforward neural nets using linear lower bounding functions, Basically, a linear lower bounding function (LLBF) for a given function over an interval is a linear function that lies below the given function and matches the original function value at one end point, To search for an adaptive step size, an LLBF for the error function, which is expressed in terms of the step size, is derived, Since the error in a neural net can never be smaller than zero, it is plausible not to take a step larger than the step size when the associated LLBF reaches zero, In this paper, an adaptive learning algorithm based on the above idea is given, Numerical examples are used to illustrate its feasibility and to compare it with some previous results.

关键词： backpropagation algorithms Neural networks Convergence Feedforward neural networks Adaptive algorithm Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

TOLERANCE TO ANALOG HARDWARE OF ON-CHIP LEARNING IN backpropagation NETWORKS

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第5期6卷 1045-1052页

作者： DOLENKO, BK CARD, HC UNIV MANITOBA WINNIPEGMB R3T 2N2CANADA

When training an artificial neural network using the popular backpropagation algorithm, implementation in dedicated analog hardware offers an attractive alternative for reasons of speed, compactness, and the lack of limited resolution in computation that is present in digital hardware, Despite these advantages, until now the use of analog hardware in backpropagation networks has been primarily limited to the forward computation, The learning computations are usually performed off-chip, because it is not immediately evident that the nonidealities inherent in analog hardware allow adequate learning to take place, In this paper we present results of simulations performed assuming both forward and backward computation are done on-chip using analog components, Aspects of analog hardware studied are component variability (variability in multiplier gains and zero offsets),limited voltage ranges, components (multipliers) that only approximate the computations in the backpropagation algorithm, and capacitive weight decay, It is shown that backpropagation networks can learn to compensate for all these shortcomings of analog circuits except for zero offsets, and the latter are correctable with minor circuit complications, Variability in multiplier gains is not a problem, and learning is still possible despite limited voltage ranges and function approximations, Fixed component variation from fabrication is shown to be less detrimental to learning than component variation due to noise, Weight decay is tolerable provided it is sufficiently:small, which implies frequent refreshing by rehearsal on the training data or modest cooling of the circuits, The former approach allows for learning nonstationary problem sets.

关键词： Computer hardware analog circuits backpropagation algorithms back propagation Learning weight decay system-on-chip Multiplying circuits

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：