检索结果-内蒙古大学图书馆

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

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

ON THE LOCAL MINIMA FREE CONDITION OF backpropagation LEARNING

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第5期6卷 1300-1303页

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

It is shown that if there are P noncoincident input patterns to learn and a two-layered feedforward neural network having P - 1 sigmoidal hidden neural and one dummy hidden neuron is used for the learning, then any suboptimal equilibrium point of the corresponding error surface is unstable in the sense of Lyapunov. This result leads to a sufficient local minima free condition for the backpropagation learning.

关键词： Neurons Neural networks backpropagation algorithms Feedforward neural networks Supervised learning Multi-layer neural network Training data Binary sequences Communication channels Sufficient conditions

来源：评论

学校读者我要写书评

暂无评论

PARALLEL, SELF-ORGANIZING, HIERARCHICAL NEURAL NETWORKS WITH CONTINUOUS INPUTS AND OUTPUTS

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第5期6卷 1037-1044页

作者： ERSOY, OK DENG, SW School of Electrical Engineering Purdue University Lafayette IN USA Electrical Engineering Department Hua-Fan College

Parallel, self organizing, hierarchical neural networks (PSHNN's) are multistage networks in which stages operate in parallel rather than in series during testing, Each stage can be any particular type of network, Previous PSHNN's assume quantized, say, binary outputs, A new type of PSHNN is discussed such that the outputs are allowed to be continuous-valued. The performance of the resulting networks is tested in the problem of predicting speech signal samples from past samples, Three types of networks in which the stages are learned by the delta rule, sequential least-squares, and the backpropagation (BP) algorithm, respectively, are described, In all cases studied, the new networks achieve better performance than linear prediction, A revised BP algorithm is discussed for learning input nonlinearities. When the BP algorithm is to be used, better performance is achieved when a single;BP network is replaced by a PSHNN of equal complexity in which each stage is a BP network of smaller complexity than the single BP network.

关键词： Neural networks Speech backpropagation algorithms Linear predictive coding Signal processing algorithms Automatic testing Mean square error methods Laser sintering Vectors Autocorrelation

来源：评论

学校读者我要写书评

暂无评论

AN EFFICIENT CONSTRAINED TRAINING ALGORITHM FOR FEEDFORWARD NETWORKS

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第6期6卷 1420-1434页

作者： KARRAS, DA PERANTONIS, SJ National Research Center Demoluitos Institute of Informatics and Telecommunications Athens Greece

A novel algorithm is presented which supplements the training phase in feedforward networks with various forms of information about desired learning properties, This information is represented by conditions which must be satisfied in addition to the demand for minimization of the usual mean square error cost function, The purpose of these conditions is to improve convergence, learning speed, and generalization properties through prompt activation of the hidden units, optimal alignment of successive weight vector offsets, elimination of excessive hidden nodes, and regulation of the magnitude of search steps in the weight space. The algorithm is applied to several small- and large-scale binary benchmark training tasks, to test its convergence ability and learning speed, as wed as to a large-scale OCR problem, to test its generalization capability. Its performance in terms of percentage of local minima, learning speed, and generalization ability is evaluated and found superior to the performance of the backpropagation algorithm and variants thereof taking especially into account the statistical significance of the results.

关键词： feedforward network algorithms backpropagation algorithms Generalization Statistical Significance Learning

来源：评论

学校读者我要写书评

暂无评论

A NEURAL-NETWORK APPROACH TO FREEWAY NETWORK TRAFFIC CONTROL

引用

CONTROL ENGINEERING PRACTICE 1995年第12期3卷 1719-1726页

作者： PAPAGEORGIOU, M MESSMER, A AZEMA, J DREWANZ, D TECH UNIV MUNICH LEHRST STEUERUNGS & REGELUNGSTECHMUNICHGERMANY

The paper investigates the application of a feedforward neural network approach to freeway network control via variable direction recommendations at bifurcation locations. A nonlinear control problem is formulated and solved first by use of computationally expensive nonlinear optimization techniques. A feedforward neural network is then trained by optimally adjusting its weights so as to reproduce the optimal control law for a limited number of traffic scenarios. Generalisation properties of the neural network are investigated and a discussion of advantages and disadvantages compared with alternative control approaches is provided.

关键词： APPLIED NEURAL CONTROL backpropagation algorithms CONJUGATE GRADIENT METHOD FEEDFORWARD NETWORKS NEURAL NETWORKS OPTIMAL CONTROL ROUTING algorithms TRAFFIC CONTROL

来源：评论

学校读者我要写书评

暂无评论

NEURAL-NET ROBOT CONTROLLER WITH GUARANTEED TRACKING PERFORMANCE

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第3期6卷 703-715页

作者： LEWIS, FL LIU, K YESILDIREK, A Automation and Robotics Research Institute University of Texas Arlington Fort Worth TX USA

A neural net (NN) controller for a general serial-link robot arm is developed. The NN has two layers so that linearity in the parameters holds, but the ''net functional reconstruction error'' and robot disturbance input are taken as nonzero. The structure of the NN controller is derived using a filtered error/passivity approach, leading to new NN passivity properties. On-line weight tuning algorithms including a correction term to backpropagation, plus an added robustifying signal, guarantee tracking as well as bounded NN weights. The NN controller structure has an outer tracking loop so that the NN weights are Conveniently initialized at zero, with learning occurring on-line in real-time. It is shown that standard backpropagation, when used for real-time closed-loop control, can yield unbounded NN weights if 1) the net cannot exactly reconstruct a certain required control function or 2) there are bounded unknown disturbances in the robot dynamics, The role of persistency of excitations explored.

关键词： Neural networks Robot control Control systems Adaptive control Nonlinear dynamical systems backpropagation algorithms Linearity Robustness Automatic control Robotics and automation

来源：评论

学校读者我要写书评

暂无评论

ROBUST RADAR TARGET CLASSIFIER USING ARTIFICIAL NEURAL NETWORKS

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第3期6卷 760-766页

作者： CHAKRABARTI, S BINDAL, N THEAGHARAJAN, K Department of Electrical Engineering and Computer Science University of Kansas Lawrence KS USA

In this paper an artificial neural network (ANN) based radar target classifier is presented, and its performance is compared with that of a conventional minimum distance classifier. Radar returns from realistic aircraft are synthesized using a thin wire time domain electromagnetic code. The time-varying backscattered electric field from each target is processed using both a conventional scheme and an ANN-based scheme for classification purposes. It is found that a multilayer feedforward ANN, trained using a backpropagation learning algorithm, provides a higher percentage of successful classification than the conventional scheme. The performance of the ANN is found to be particularly attractive in an environment of low signal-to-noise ratio. The performance of both methods are also compared when a preemphasis filter is used to enhance the contributions from the high frequency poles in the target response.

关键词： Robustness Artificial neural networks Airborne radar Aircraft Network synthesis Wire Nonhomogeneous media backpropagation algorithms Signal to noise ratio Filters

来源：评论

学校读者我要写书评

暂无评论

TOWARDS THE REALIZATION OF AN ARTIFICIAL TACTILE SYSTEM - FINE-FORM DISCRIMINATION BY A TENSORIAL TACTILE SENSOR ARRAY AND NEURAL INVERSION algorithms

引用

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS 1995年第6期25卷 933-946页

作者： CAITI, A CANEPA, G DEROSSI, D GERMAGNOLI, F MAGENES, G PARISINI, T UNIV PISA CTR PIAGGIOPISAITALY UNIV PAVIA DEPT COMP & SYST SCIPAVIAITALY

This paper describes techniques and methodologies so far developed to investigate object fine-form discrimination by means of artificial tactile sensors. Sensor arrays, selectively sensitive to stress-tenser components and based on piezoelectric polymer technology, have been realized. Sensor output data are used to solve inverse elastic contact problems, by means of neural networks suitably trained to learn regularized inverse maps. Two possible neural network designs are considered: one is based on the multi-layer perceptron trained with the standard backpropagation algorithm, and the other is based on the use of radial basis functions. In both cases, reconstruction of object shapes is demonstrated to be effective and robust with both simulated and real data.

关键词： Multilayer perceptrons stress tensor Tensor backpropagation algorithms Neural network Sensor arrays tactile sensors

来源：评论

学校读者我要写书评

暂无评论

ONLINE LEARNING WITH MINIMAL DEGRADATION IN FEEDFORWARD NETWORKS

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第3期6卷 657-668页

作者： DEANGULO, VR TORRAS, C INST CIBERNET E-08028 BARCELONASPAIN

Dealing with nonstationary processes requires quick adaptation while at the same time avoiding catastrophic forgetting, A neural learning technique that satisfies these requirements, without sacrifying the benefits of distributed representations, is presented, It relies on a formalization of the problem as the minimization of the error over the previously learned input-output (i-o) patterns, subject to the constraint of perfect encoding of the new pattern, Then this constrained optimization problem is transformed into an unconstrained one with hidden-unit activations as variables. This new formulation naturally leads to an algorithm for solving the problem, which we call learning with minimal degradation (LMD), Some experimental comparisons of the performance of LMD with back propagation are provided which, besides showing the advantages of using LMD, reveal the dependence of forgetting on the learning fate in backpropagation. We also explain why overtraining affects forgetting and fault tolerance, which are seen as related problems.

关键词： Degradation Intelligent networks backpropagation algorithms Interference Encoding Constraint optimization Fault tolerance Adaptive systems Systems engineering and theory Informatics

来源：评论

学校读者我要写书评

暂无评论

DIAGONAL RECURRENT NEURAL NETWORKS FOR DYNAMIC-SYSTEMS CONTROL

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS 1995年第1期6卷 144-156页

作者： KU, CC LEE, KY Department of Electrical and Computer Engineering Pennsylvania State University University Park PA USA

A new neural paradigm called diagonal recurrent neural network (DRNN) is presented. The architecture of DRNN is a modified model of the fully connected recurrent neural network with one hidden layer, and the hidden layer is comprised of self-recurrent neurons. Two DRNN's are utilized in a control system, one as an identifier called diagonal recurrent neuroidentifier (DRNI) and the other as a controller called diagonal recurrent neurocontroller (DRNC). A controlled plant is identified by the DRNI, which then provides the sensitivity information of the plant to the DRNC. A generalized dynamic backpropagation algorithm (DBP) is developed and used to train both DRNC and DRNI. Due to the recurrence, the DRNN can capture the dynamic behavior of a system. To guarantee convergence and for faster learning, an approach that uses adaptive learning rates is developed by introducing a Lyapunov function. Convergence theorems for the adaptive backpropagation algorithms are developed for both DRNI and DRNC. The proposed DRNN paradigm is applied to numerical problems and the simulation results are included.

关键词： Recurrent neural networks Control systems Neural networks backpropagation algorithms Feedforward neural networks Neurons Convergence Adaptive control Dynamic programming Intelligent control

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：