检索结果-内蒙古大学图书馆

AN IMPROVED DIGIT-REVERSAL PERMUTATION ALGORITHM

SIGNAL PROCESSING 1993年第3期32卷 409-415页

作者： YU, XG LOH, NK MILLER, WC [a]Department of Electrical Engineering University of Windsor Windsor Ontario Canada N9B 3P4 [b]Center for Robotics Advanced Automation Dodge Hall of Engineering Oakland University Rochester MI48309-4401 USA

This paper introduces a new structure to compute the digit-reversal permutation in the radix-B fast Fourier or Hartley transform. By studying the property of base-B numbers, we find that any base-B number, k, can be represented as the sum of three numbers: one base-B number, i;digital reverse of another base-B number, j;and a constant, z, in which the two base-B numbers i and j are no greater than square-root N, where N is the number of data points to be transformed. Then, the digital reverse of k is just the sum of j and the digital reverse of i plus the constant z. Using this property we have developed a new algorithm to compute the digital reverse of any index very efficiently. Since it uses fewer arithmetic operations, the new algorithm is faster than other algorithms known to the authors and the program storage requirements are no greater than Evans' and Walker's algorithms.

关键词： FAST FOURIER TRANSFORM FAST HARTLEY TRANSFORM DIGIT-REVERSAL PERMUTATION BIT-REVERSE ALGORITHM

来源：评论

学校读者我要写书评

暂无评论

Modified backpropagation algorithms for training the multilayer feedforward neural networks with hard-limiting neurons

Modified backpropagation algorithms for training the multila...

引用

1993 Canadian Conference on Electrical and Computer engineering, CCECE 1993

作者： Yu, Xiangui Loh, N.K. Jullien, G.A. Miller, W.C. Dept. of Electrical Engineering University of Windsor WindsorONN9B 3P4 Canada Center for Robotics and Advanced Automation Dodge Hall of Engineering Oakland University RochesterMI48309-4401 United States

ISBN: (纸本)0780314433

This paper introduces modified backpropagation algorithms for training multilayer feedforward neural networks with hard-limiting neurons. Transforming neuron activation functions are used in all the hidden layers, which are the modified continuous sigmoidal functions with an adaptive steepness factors. In the training process, this steepness factor varies from a small positive value to infinite with the decrease of the sum square error. Thus, a multilayer feedforward neural network can be trained with the resultant architecture only composed of hard limiting neurons. The learning algorithm is similar to the conventional backpropagation algorithm. Only the derivatives of the hidden neural activation functions are modified. Extensive numerical simulations are presented to show the feasibility of the proposed algorithm. In addition, the numerical properties of the proposed algorithm are discussed and comparisons of the proposed algorithm with other algorithms are made. © 1993 IEEE.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

The design and training of an intelligent sensor implementation

The design and training of an intelligent sensor implementat...

引用

1993 Canadian Conference on Electrical and Computer engineering, CCECE 1993

ISBN: (纸本)0780314433

The design and VLSI implementation of an intelligent sensor that can be used for process control applications requiring image capture or non-contact measurement is presented in this paper. The sensor architecture is based on an analog VLSI realization of an artificial neural network with an integrated photosensitive array. A 10×10 array of photosensitive cells has been designed as the input nodes to a two-layer feedforward neural network. Four groups each with 25 photosensors are fully connected to 4 neurons respectively in the hidden layer. The 16 hidden neurons are fully connected to 5 neurons in the output layer. A development program has been written that determines the optimal set of weights using the modified backpropagation algorithm. The neural network has been trained to recognize 18 different types of patterns. The final implementation of this intelligent sensor has the dimensions of 4500×4820 design scale microns and contains approximately 1630 analog devices fabricated using a 3μ single-polysilicon, double-metal, p-well CMOS process. © 1993 IEEE.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Comparisons of four learning algorithms for training the multilayer feedforward neural networks with hard-limiting neurons

Comparisons of four learning algorithms for training the mul...

引用

1993 Canadian Conference on Electrical and Computer engineering, CCECE 1993

ISBN: (纸本)0780314433

In this paper, two kinds of learning algorithms that have been developed for training multilayer feedforward neural networks with hard-limiting neurons are reviewed. For the modified backpropagation algorithms, their numerical performances of convergence speed and training efficiency are compared;for the architecture generating methods, the architecture sizes of the neural networks generated are compared and their generalization ability are discussed. For any given application problem, some criteria for selecting a suitable training algorithm are also discussed. © 1993 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Comparisons of four learning algorithms for training the multilayer feedforward neural networks with hard-limiting neurons

Comparisons of four learning algorithms for training the mul...

引用

Canadian Conference on Electrical and Computer engineering (CCECE)

作者： Xiangui Yu N.K. Loh G.A. Jullien W.C. Miller Department of Electrical Engineering University of Windsor Windsor ONT Canada Center for Robotics and Advanced Automation Dodge Hall of Engineering Oakland University Rochester MI USA

In this paper, two kinds of learning algorithms that have been developed for training multilayer feedforward neural networks with hard-limiting neurons are reviewed. For the modified backpropagation algorithms, their numerical performances of convergence speed and training efficiency are compared; for the architecture generating methods, the architecture sizes of the neural networks generated are compared and their generalization ability are discussed. For any given application problem, some criteria for selecting a suitable training algorithm are also discussed.< >

关键词： Multi-layer neural network Neural networks Feedforward neural networks Neurons Backpropagation algorithms Artificial neural networks robotics and automation Electronic mail Convergence of numerical methods Multilayer perceptrons

来源：评论

学校读者我要写书评

暂无评论

The design and training of an intelligent sensor implementation

The design and training of an intelligent sensor implementat...

引用

Canadian Conference on Electrical and Computer engineering (CCECE)

The design and VLSI implementation of an intelligent sensor that can be used for process control applications requiring image capture or non-contact measurement is presented in this paper. The sensor architecture is based on an analog VLSI realization of an artificial neural network with an integrated photosensitive array. A 10/spl times/10 array of photosensitive cells has been designed as the input nodes to a two-layer feedforward neural network. Four groups each with 25 photosensors are fully connected to 4 neurons respectively in the hidden layer. The 16 hidden neurons are fully connected to 5 neurons in the output layer. A development program has been written that determines the optimal set of weights using the modified backpropagation algorithm. The neural network has been trained to recognize 18 different types of patterns. The final implementation of this intelligent sensor has the dimensions of 4500/spl times/4820 design scale microns and contains approximately 1630 analog devices fabricated using a 3/spl mu/ single-polysilicon, double-metal, p-well CMOS process.< >

关键词： Intelligent sensors Sensor arrays Neurons Very large scale integration Artificial neural networks Neural networks Process control Feedforward neural networks Backpropagation algorithms Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Training hard-limiting neurons using back-propagation algorithm by updating steepness factors

Training hard-limiting neurons using back-propagation algori...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiangui Yu N.K. Loh W.C. Miller Department of Electrical Engineering University of Windsor Windsor ONT Canada Center for Robotics and Advanced Automation Dodge Hall of Engineering Oakland University Rochester MI USA

This paper presents one kind of modified backpropagation algorithm for training the multilayer feedforward neural networks with hard-limiting neurons. Adaptive steepness factors in the analog sigmoidal neuron activation functions are updated in the training process. With the decrease of the sum-square error, these steepness factors are varied from a small positive value to infinite. It makes the sigmoidal neuron transferred to hard-limiting one after the training process complete. Thus, a multilayer feedforward neural network can be trained with the resultant architecture is only composed of hard-limiting neurons. The learning algorithm is similar to the conventional backpropagation algorithm, only the derivatives of the hidden neural activation functions are modified according to the proposed idea. Extensive numerical simulations are presented to show the feasibility of the proposed algorithm. In addition, the numerical properties of the proposed algorithm are also discussed in detail. Comparisons of the proposed algorithm with algorithms are given, and some useful conclusions are drawn.< >

关键词： Neurons Backpropagation algorithms Multi-layer neural network Neural networks Feedforward neural networks Very large scale integration robotics and automation Multilayer perceptrons Numerical simulation Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Modified backpropagation algorithms for training the multilayer feedforward neural networks with hard-limiting neurons

Modified backpropagation algorithms for training the multila...

引用

Canadian Conference on Electrical and Computer engineering (CCECE)

关键词： Multi-layer neural network Backpropagation algorithms Neural networks Feedforward neural networks Neurons Multilayer perceptrons Very large scale integration robotics and automation Electronic mail Numerical simulation

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：