检索结果-内蒙古大学图书馆

IEEE International Symposium on circuits and systems (ISCAS)

作者： F.M. Salam Circuits Systems and Artificial Neural Networks Laboratory Department of Electrical Engineering Michigan State University East Lansing MI USA

We present results of several experiments of a neural network with temporal learning on a single chip. The single chip configuration is a 2-D scalable array with learning constructed via simple modular CMOS building blocks. We report on learning prototype periodic temporal signals which may be displayed as a closed curve, a figure-8 shape, or an arbitrary periodic or aperiodic shapes in the state space. The experiments demonstrate the instantaneous learning by the chip of these shapes.

关键词： Process control Neurons Testing Shape Frequency Displays Recurrent neural networks Differential equations Time measurement Limit-cycles

来源：评论

学校读者我要写书评

暂无评论

Algorithms for blind signal separation and recovery in static and dynamic environments

Algorithms for blind signal separation and recovery in stati...

引用

IEEE International Symposium on circuits and systems (ISCAS)

作者： A.B. Gharbi F.M. Salam Circuits Systems and Artificial Neural Networks LaboratoryDepartment of Electrical Engineering Michigan State University East Lansing MI USA

We propose update laws for the problem of blind separation in static and dynamic environments. The energy function is based on an approximation of the mutual information as a measure of independence. Both feedforward and feedback structures of the neural network are considered. A general framework to develop the update law for the dynamic model is proposed. Computer simulations to support the analytical work are provided.

关键词： Blind source separation Mutual information Energy measurement State-space methods State feedback IIR filters Filtering Linear systems Intelligent networks circuits

来源：评论

学校读者我要写书评

暂无评论

A neuro-chip with temporal learning: test results for signal/shape generation

A neuro-chip with temporal learning: test results for signal...

引用

Asilomar Conference on Signals, systems & Computers

作者： F.M. Salam Circuits Systems and Artificial Neural Networks Laboratory Department of Electrical Engineering Michigan State University East Lansing MI USA

We briefly describe a recently designed neural network with temporal learning. The developed learning rule extends the temporal learning to realize a forward instantaneous update scheme, suitable for complete analog hardware implementation. The single chip configuration is a two-dimensional scalable array with learning constructed via simple scalable CMOS building blocks. We report on extensive test results of learning prototype periodic temporal signals which may be displayed as a closed curve or a figure-8 shape in the state space. Several experimental tests demonstrating the instantaneous learning by the chip of these shapes are reported.

关键词： Testing Shape Signal generators Recurrent neural networks artificial neural networks Hardware Signal processing algorithms State-space methods Signal processing Control systems

来源：评论

学校读者我要写书评

暂无评论

Formulation and algorithms for blind signal recovery

Formulation and algorithms for blind signal recovery

引用

Midwest Symposium on circuits and systems (MWSCAS)

作者： F.M. Salam A.B. Gharbi G. Erten Circuits Systems and Artificial Neural Networks Laboratory Department of Electrical Engineering Michigan State University East Lansing MI USA Michigan State University East Lansing MI US Dept. of Electr. Eng. Michigan State Univ. East Lansing MI USA IC Tech Inc. Okemos MI USA

We review some recent approximations of the averaged mutual information criterion and its use as a measure of signal independence. We describe an update law and its comparison with previous work in the literature. We also identify the link between the minimization of the mutual information and the information-maximization of the output entropy function of a (nonlinear) neural network. Example simulations demonstrate the performance of our recently developed algorithm in static and dynamic environments.

关键词： Mutual information neural networks Finite impulse response filter Density measurement circuits artificial neural networks laboratories Aging Electric variables measurement Minimization

来源：评论

学校读者我要写书评

暂无评论

Implementation and experimental results of a chip for the separation of mixed and filtered signals

引用

JOURNAL OF circuits systems AND COMPUTERS 1996年第2期6卷 115-138页

作者： Gharbi, ABA Salam, FMA Circuits Systems and Artificial Neural Networks Laboratory Department of Electrical Engineering Michigan State University East Lansing MI 48824 USA

We describe an algorithm and chip implementation for separating a mixture of unknown, but independent, temporal signals in static and dynamic environments. The proposed algorithm, which is a simple modification of the Herault and Jutten (HJ) algorithm, proved to be robust to parameter variations in both cases. We present chip test results to quantify the performance of the modified algorithm in static and dynamic (mixing and filtering) environments. Moreover, experiments of separating two speech or two music signals in English-English, English-Japanese, and English-Arabic have demonstrated successful performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-time tracking control using modular neural chips with on-chip learning

Real-time tracking control using modular neural chips with o...

引用

International Conference on neural networks

作者： F.M. Salam Hwa-Joon Oh Circuits Systems & Artificial neural networks Laboratory Department of Electrical Engineering Michigan State University East Lansing MI USA

We employ a modular analog chip of a neural architecture with continuous-time learning in a real-time control of a prototype physical system. The novel control structure and the experiments demonstrate the capability of the modular chips in applications that enhance system performance and which achieve calibration in real-time. The chips represent a new class of reconfigurable real-time controllers which can self-adapt to regulate, steer, or track a given profile without explicit mathematical modeling.

关键词： neural network hardware Control systems Industrial control Automatic control Power system modeling neural networks Network-on-a-chip Real time systems Automotive engineering Manufacturing automation

来源：评论

学校读者我要写书评

暂无评论

Nonlinear projection to submanifolds using neural networks with circuit realization and its application to data reduction

Nonlinear projection to submanifolds using neural networks w...

引用

IEEE International Symposium on circuits and systems (ISCAS)

作者： F.M.A. Salam G. Erten S. Vedula Hwa-Joon Oh Circuits and Systems and Artificial Neural Networks Laboratories Department of Electrical Engineering Michigan State University East Lansing MI USA IC Tech Inc. Okemos MI USA

The Principal Component Analysis (PCA) approach and its variations compute eigenvalues and eigenvectors and hence planar surfaces. An extension of the PCA approach, which computes nonplanar (folded) surfaces, is a computational tool that computes submanifolds in higher dimensional spaces. The focus of this work is an application of this nonlinear projection approach to nonlinear data reduction/compression of color images and 3-band radar signals. Results of various image processing from both computer simulations of the circuit model and chip experiments are reported. Furthermore, we describe how certain neural networks can be constructed as computational tools for general submanifold charts and parameterization maps of nonlinear dynamical systems. Moreover, the architectural framework is compatible with basic circuit realization using micropower microelectronic components.

关键词： neural networks Principal component analysis circuits Eigenvalues and eigenfunctions Focusing Application software Image coding Color Radar applications Radar imaging

来源：评论

学校读者我要写书评

暂无评论

Convergence to satisfactory minima of the extended Kalman filter algorithm for supervised learning 29

Convergence to satisfactory minima of the extended Kalman fi...

引用

29th Asilomar Conference on Signals, systems and Computers, ACSSC 1995

作者： Benromdhane, Saida Salam, Fathi M.A. Circuits and Systems and Artificial Neural Networks Laboratory Department of Electrical Engineering Michigan State University East LansingMI48824 United States

ISBN: (纸本)0818673702

Present, training algorithms for feedforward artificial neural networks do get trapped in local minima. Some of these minima are satisfactory in terms of desired performance but many are not. When the weights converge to an unsatisfactory local minimum, the choice usually is to restart the algorithm from a different initial condition, hoping to achieve a better solution. In this paper we suggest practical ways and techniques to solve the problem of convergence to unsatisfactory local minima without the inconvenience of restarting the algorithm. A comparison of the performance of the improved algorithm with the original one will be presented through computer simulations of region classification problems. © 1996 IEEE

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Implementation and test results of a chip for the separation of mixed signals

Implementation and test results of a chip for the separation...

引用

IEEE International Symposium on circuits and systems (ISCAS)

作者： A.B.A. Gharbi F.M.A. Salam Circuits Systems and Artificial Neural Networks Laboratory Department of Electrical Engineering Michigan State University East Lansing MI USA

We describe an algorithm and chip implementation for separating a mixture of unknown, but independent, temporal signals in static and dynamic environments. The proposed algorithm, which is a simple modification of the Herault and Jutten (HJ) algorithm, proved to be robust to parameter variations. Moreover, we present some chip results to quantify the performance of the modified algorithm in static and dynamic (mixing and filtering) environments.

关键词： Robustness Circuit testing Voltage Semiconductor device measurement Semiconductor device modeling CMOS technology Equations Delay Vectors Smoothing methods

来源：评论

学校读者我要写书评

暂无评论

Convergence to satisfactory minima of the extended Kalman filter algorithm for supervised learning

Convergence to satisfactory minima of the extended Kalman fi...

引用

Asilomar Conference on Signals, systems & Computers

作者： S. Benromdhane F.M.A. Salam Circuits arid Systems and Artificial Neural Networks Laboratory Michigan State University East Lansing MI USA Michigan State University East Lansing MI US

Present training algorithms for feedforward artificial neural networks do get trapped in local minima. Some of these minima are satisfactory in terms of desired performance but many are not. When the weights converge to an unsatisfactory local minimum, the choice usually is to restart the algorithm from a different initial condition, hoping to achieve a better solution. We suggest practical ways and techniques to solve the problem of convergence to unsatisfactory local minima without the inconvenience of restarting the algorithm. A comparison of the performance of the improved algorithm with the original one is presented through computer simulations of region classification problems.

关键词： Convergence Supervised learning Backpropagation algorithms artificial neural networks Filtering algorithms Kalman filters Equations Covariance matrix laboratories Computer 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：