检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Marco Aurelio Nuno-Maganda Miguel Arias-Estrada Cesar Torres-Huitzil Bernard Girau Computer Science Department National Institute for Astrophysics Optics and Electronics Puebla Mexico Information Technology Department Polytechnic University of Victoria Ciudad Victoria Tamaulipas Mexico CORTEX-TEAM LORIA INRIA Vandoeuvre-les-Nancy France

Spiking Neural Networks (SNNs) have become an important research theme due to new discoveries and advances in neurophysiology, which states that information among neurons is interchanged via pulses or spikes. FPGAs are widely used for implementing high performance digital hardware systems, due to its flexibility and because they are suitable for the implementation of systems with high degree of parallelism. FPGAs have become an important tool because fine grain digital elements useful for efficient hardware implementation of SNNs are provided, making FPGA device suitable for implementing SNNs. Several attempts for implementing efficient classifiers in hardware have been done, but most of them fail because the processing elements are costly in terms of hardware resource utilization. SNNs are less hardware greedy, and the nature of the pulsed processing is well suited to the digital processing blocks of the FPGA devices. In this work, a hardware architecture for implementing both recall and learning phases required for Multilayer FeedForward SNNs is proposed. Results and performance statics are provided.

关键词： Neural network hardware Neural networks backpropagation algorithms Neurons Field programmable gate arrays Artificial neural networks Biological system modeling Logic devices Programmable logic arrays Programmable logic devices

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

Controllable pitch propeller control with fast backpropagation algorithm

引用

MARINE TECHNOLOGY AND SNAME NEWS 2007年第3期44卷 180-184页

作者： Alarcin, Fuat Ekinci, Serkan Gulez, Kayhan Yildiz Tech Univ Dept Naval Architecture & Marine Engn Istanbul Turkey Yildiz Tech Univ Dept Elect Engn Istanbul Turkey

In this paper, controllable pitch propeller (CPP) has been used to improve the maneuvering at a fixed shaft speed. The proportional-derivative (PD) control method has been applied to obtain high efficiency by changing the pitch angle. The controller results have been evaluated and learned by a fast backpropagation algorithm (FBA). The neural network results show that learning of pitch behavior has been verified, and the FBA performance of CPP controller is better than that of the PD controller.

关键词： Fasting Controllers CPP gene Maneuvering backpropagation algorithms Learning Controllable pitch propellers angle of pitch

来源：评论

学校读者我要写书评

暂无评论

backpropagation AND COUNTER-PROPAGATION NEURAL NETWORKS FOR PHYLOGENETIC CLASSIFICATION OF RIBOSOMAL-RNA SEQUENCES

引用

NUCLEIC ACIDS RESEARCH 1994年第20期22卷 4291-4299页

作者： WU, C SHIVAKUMAR, S Department of Epidemiology/Biomathematics University of Texas Health Center at Tyler 75710.

A neural network system has been developed for rapid and accurate classification of ribosomal RNA sequences according to phylogenetic relationship. The molecular sequences are encoded into neural input vectors using an n-gram hashing method. A SVD (singular value decomposition) method is used to compress and reduce the size of long and sparse n-gram input vectors. The neural networks used are three-layered, feed-forward networks that employ supervised learning paradigms, including the backpropagation algorithm and a modified counter-propagation algorithm. A pedagogical pattern selection strategy is used to reduce the training time. After trained with ribosomal RNA sequences of the RDP (Ribosomal Database Project) database, the system can classify query sequences into more than one hundred phylogenetic classes with a 100% accuracy at a rate of less than 0.3 CPU second per sequence on a workstation. When compared to other sequence similarity search methods, including Similarity Rank, Blast and Pasta, the neural network method has a higher classification accuracy at a speed of about an order of magnitude faster. The software tool will be made available to the biology community, and the system may be extended into a gene identification system for classifying indiscriminately sequenced DNA fragments.

关键词： Singular value decomposition Sequences Workstations Software Tools Taxonomy backpropagation algorithms back propagation Ribosomal RNA Neural network

来源：评论

学校读者我要写书评

暂无评论

PERFORMANCE ANALYSIS OF A PIPELINED backpropagation PARALLEL ALGORITHM

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1993年第6期4卷 970-981页

作者： PETROWSKI, A DREYFUS, G GIRAULT, C ECOLE SUPER PHYS & CHIM IND VILLE PARIS ELECTR LABF-75005 PARISFRANCE UNIV PARIS 06 MASICNRSIBP LABF-75252 PARIS 05FRANCE FRANCE TELECOM MEYLANFRANCE

The supervised training of feedforward neural networks is often based on the error backpropagation algorithm. Our main purpose is to consider the successive layers of a feedforward neural network as the stages of a pipeline which is used to improve the efficiency of the parallel algorithm. A simple placement rule will be presented in order to take advantage of simultaneous executions of the calculations on each layer of the network The analytic expressions show that the parallelization is efficient. Moreover, they indicate that the performances of this implementation are almost independent of the neural network architecture. Their simplicity assures easy prediction of learning performance on a parallel machine for any neural network architecture. The experimental results are in agreement with analytical estimates.

关键词： Performance analysis Parallel algorithms Neural networks Neurons Partitioning algorithms Feedforward neural networks backpropagation algorithms Artificial neural networks Machine learning Data communication

来源：评论

学校读者我要写书评

暂无评论

Use of genetic algorithms with backpropagation in training of feedforward neural networks

Use of genetic algorithms with backpropagation in training o...

引用

International Conference on Neural Networks

作者： M. McInerney A.P. Dhawan Dept. of Phys. Rose-Hulman Inst. Terre Haute IN USA Department of Electrical and Computer Engineering University of Cincinnati Cincinnati OH USA

Genetic algorithms are searching strategies available for finding the globally optimal solution. The problem of genetic algorithms is that they are inherently slow. A hybrid of genetic and backpropagation algorithms (GA-BP) that should always find the correct global minima without getting stuck at local minima is presented. Various versions of the GA-BP method are presented and experimental results show that GA-BP algorithms are as fast as the backpropagation algorithm and do not get stuck at local minima. The proposed GA-BP algorithms are also not sensitive to the values of momentum and learning rate used in backpropagation and can be made independent of the learning rate and momentum. It is shown that the adaptive GA-BP algorithm can provide the optimal learning rate and better performance than simple backpropagation.< >

关键词： Genetic algorithms Intelligent networks Neural networks Feedforward neural networks Physics backpropagation algorithms Feeds Multilayer perceptrons Robustness Feedforward systems

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

Accelerating convolutional neural network training using ProMoD backpropagation algorithm

引用

IET IMAGE PROCESSING 2020年第13期14卷 2957-2964页

作者： Gurhanli, Ahmet Istanbul Aydin Univ Dept Comp Engn Besyol Mah Inonu Cad 38 Sefakoy Kucukcekmece Istanbul Turkey

Convolutional neural networks (CNNs) play an important role in image recognition applications. Fast training of image recognition systems is a crucial point, because the system should be trained for each new image class. These networks are trained using lengthy calculations. Focus of engineering is on obtaining a fast, but stable optimisation method. Momentum technique which is used in backpropagation algorithms is like a proportional-integral (PI) controller that is widely employed in automatic control systems. It takes the integral of past errors and helps reaching the training targets. Proportional + momentum + derivative (ProMoD) method adds gradient of update matrices to the training process and builds an optimiser such as the widely used PI-derivative controller. The method accelerates the movement toward the target accuracy levels. This is achieved by doing bigger corrections in the beginning using the differences in the calculated update matrices. In this research, ProMoD method is tested on image recognition applications and CNNs. Modified national institute of standards and technology database (MNIST) and Fashion-MNIST datasets are used for evaluating the performance. Experimental results showed that ProMoD might perform much faster in training of CNNs and consume proportionally less power with respect to the momentum and stochastic gradient descent (SGD) techniques.

关键词： gradient methods backpropagation image recognition learning (artificial intelligence) convolutional neural nets convolutional neural network training ProMoD backpropagation algorithm convolutional neural networks CNN image recognition applications fast training image recognition systems crucial point image class lengthy calculations stable optimisation method momentum technique backpropagation algorithms proportional-integral controller automatic control systems training targets proportional plus momentum plus derivative method training process PI-derivative controller target accuracy levels calculated update matrices ProMoD method

来源：评论

学校读者我要写书评

暂无评论

A FAST FILTERED backpropagation ALGORITHM FOR ULTRASOUND TOMOGRAPHY

引用

IEEE TRANSACTIONS ON ULTRASONICS FERROELECTRICS AND FREQUENCY CONTROL 1987年第3期34卷 330-340页

作者： DEVANEY, AJ A. J. Devaney Associates Inc. Ridgefield CT USA

Ultrasound tomography of acoustic objects having variable density and compressibility is addressed within the framework of diffraction tomography. The filtered backpropagation algorithm of diffraction tomography is reviewed for tomographic systems employing plane-wave insonification and fixed (nonrotating) measurement planes. For these systems it is shown that a fast version of the algorithm can be implemented that requires on the order of M × N_xfewer discrete Fourier transforms (DFT’s) than are required by the conventional filtered backpropagation algorithm where M is the total number of views and N_xthe length of the image array along the axis perpendicular to the receiver plane. The conventional and fast algorithms are implemented in Fortran on a microcomputer and tested in computer simulation studies. It is found that both algorithms yield identical reconstructions;however, the fast algorithm results in considerable savings of CPU time. A detailed discussion of the implementation of both the conventional and fast filtered backpropagation algorithms on a microcomputer as well as graphs and photographic images of reconstruction generated using readily available and inexpensive commercial software and hardware are included. © 1987 IEEE

关键词： backpropagation algorithms Ultrasonic imaging Image reconstruction Interpolation Fourier transforms Partial differential equations X-ray tomography Detectors Stacking Acoustic diffraction

来源：评论

学校读者我要写书评

暂无评论

Parallel implementation of backpropagation neural networks on a heterogeneous array of transputers

引用

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS 1997年第1期27卷 118-126页

作者： Foo, SK Saratchandran, P Sundararajan, N Centre for Signal Processing School of Electrical and Electronic Engineering Nanyang Technological University Singapore

This paper analyzes parallel implementation of the backpropagation training algorithm on a heterogeneous transputer network (i.e., transputers of different speed and memory) connected in a pipelined ring topology. Training-set parallelism is employed as the parallelizing paradigm for the backpropagation algorithm. It is shown through analysis that finding the optimal allocation of the training patterns amongst the processors to minimize the time for a training epoch is a mixed integer programming problem. Using mixed integer programming optimal pattern allocations for heterogeneous processor networks having a mixture of T805-20 (20 MHz) and T805-25 (25 MHz) transputers are theoretically found out for two benchmark problems. The time for an epoch corresponding to the optimal pattern allocations is then obtained experimentally for the benchmark problems from the 805-20, T805-25 heterogeneous networks. A Monte Carlo simulation study is carried out to statistically verify the optimality of the epoch time obtained from the mixed integer programming based allocations. In this study pattern allocations are randomly generated and the corresponding time for ap epoch is experimentally obtained from the heterogeneous network. The mean and standard deviation for the epoch times from the random allocations are then compared with the optimal epoch time. The results show the optimal epoch time to be always lower than the mean epoch times by more than three standard deviations (3 sigma) for all the sample sizes used in the study thus giving validity to the theoretical analysis.

关键词： Neural networks backpropagation algorithms Linear programming Multi-layer neural network Neurons Algorithm design and analysis Network topology Pattern analysis Parallel machines Pipeline processing

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：