Many proposals have been presented for the acquisition of inverse models in multilayered neural networks. However, most are concerned with the backpropagation rule or its improvement. In learning in a multilayered neu...
详细信息
Many proposals have been presented for the acquisition of inverse models in multilayered neural networks. However, most are concerned with the backpropagation rule or its improvement. In learning in a multilayered neural network based on the backpropagation rule, there must be a supervisor signal for the output layer, and there must be a particular path to propagate the learning signal in the reverse direction. In addition, convergence is slow due to the use of the method of steepest descent in updating the weights. Consequently, this paper proposes a forward propagation rule in which the neural network model is trained by propagating the motion error exhibited by the control object in the forward direction in the neural network. In the proposed algorithm, the extended Newton's method is used to derive the goal signal (which corresponds to the supervisor signal) in the hidden layer and the output layer. Since linear multiple regression can be used in weight updating for realizing the goal signals, the iteration of weight updating can be reduced compared to the method of steepest descent. A computer simulation was performed for acquisition of a two-link arm model, and the effectiveness of the proposed learning scheme was verified. (C) 2005 Wiley Periodicals, Inc.
Functional verification is the bottleneck in delivering today's highly integrated electronic systems and chips. We should notice the simulation times and computation resource challenge in the automatic pseudo-rand...
详细信息
ISBN:
(纸本)0780387368
Functional verification is the bottleneck in delivering today's highly integrated electronic systems and chips. We should notice the simulation times and computation resource challenge in the automatic pseudo-random test generation and a novel solution named Priority Directed test Generation (PDG) is proposed in this paper. With PDG, a test vector which hasn't been simulated is granted a priority attribute. The priority indicates the possibility of detecting new bugs by simulating this vector. We show how to apply Artificial Neural Networks (ANNs) learning algorithm to the PDG problem. Several experiments are given to exhibit how to achieve better result in this PDG method.
Among other domains, learning finite-state machines is important for obtaining a model of a system under development, so that powerful formal methods such as model checking can be applied. A prominent algorithm for le...
详细信息
Among other domains, learning finite-state machines is important for obtaining a model of a system under development, so that powerful formal methods such as model checking can be applied. A prominent algorithm for learning such devices was developed by Angluin. We have implemented this algorithm in a straightforward way to gain further insights to practical applicability. Furthermore, we have analyzed its performance on randomly generated as well as real-world examples. Our experiments focus on the impact of the alphabet size and the number of states on the needed number of membership queries. Additionally, we have implemented and analyzed an optimized version for learning prefix-closed regular languages. Memory consumption is one major obstacle when we attempted to learn large examples. We see that prefix-closed languages are relatively hard to learn compared to arbitrary regular languages. The optimization, however, shows positive results.
This paper proposes a new feedrate control technique of CNC that can achieve high machining accuracy and high productivity. The proposed adaptive neuro-controller adjusts both components of the feedrate and makes an i...
详细信息
This paper proposes a new feedrate control technique of CNC that can achieve high machining accuracy and high productivity. The proposed adaptive neuro-controller adjusts both components of the feedrate and makes an improved command of contour geometry. This control architecture consists of a neural network identifier (NNI) and an iterative learning algorithm with inversion of the NNI. The NNI is an identifier for the non-linear characteristics of CNC and composed of two outputs that are identified with individual axis dynamics of the contour error. The iterative learning algorithm is exploited to derive an optimal feedrate control law by minimizing a performance index that is a measurement of the contour error and the machining time.
Due to the uncertainty of many of the factors that influence the performance of an emergency medical service, we propose using Bayesian networks to model this kind of system. We use different algorithms for learning B...
详细信息
Due to the uncertainty of many of the factors that influence the performance of an emergency medical service, we propose using Bayesian networks to model this kind of system. We use different algorithms for learning Bayesian networks in order to build several models, from the hospital manager's point of view, and apply them to the specific case of the emergency service of a Spanish hospital. This first study of a real problem includes preliminary data processing, the experiments carried out, the comparison of the algorithms from different perspectives, and some potential uses of Bayesian networks for management problems in the health service. (C) 2004 Elsevier B.V. All rights reserved.
Time series prediction plays an important role in engineering applications. Artificial neural networks seem to be a useful tool to solve these problems. However, in real engineering, the inputs and outputs of many com...
详细信息
Time series prediction plays an important role in engineering applications. Artificial neural networks seem to be a useful tool to solve these problems. However, in real engineering, the inputs and outputs of many complicated systems are time-varied functions. Conventional artificial neural networks are not suitable to predicting time series in these systems directly. In order to overcome this limitation, a parallel feedforward process neural network (PFPNN) is proposed. The inputs and outputs of the PFPNN are time-varied functions, which makes it possible to predict time series directly. A corresponding learning algorithm for the PFPNN is developed. To simplify this learning algorithm, appropriate orthogonal basis functions are selected to expand the input functions, output functions and network weight functions. The effectiveness of the PFPNN and its learning algorithm is proved by the Mackey-Glass time series prediction. Finally, the PFPNN is utilized to predict exhaust gas temperature time series in aircraft engine condition monitoring, and the simulation test results also indicate that the PFPNN has a faster convergence speed and higher accuracy than the same scale multilayer feedforward process neural network.
A modular approach for improving the performance of 2-D Hopfield neural network is presented in this paper. The approach is inspired by biological visual perception phenomenon. The training method introduces a decayin...
详细信息
A modular approach for improving the performance of 2-D Hopfield neural network is presented in this paper. The approach is inspired by biological visual perception phenomenon. The training method introduces a decaying distance factor into the Hebbian learning rule for image processing applications. The value of the distance factor varies based on the spatial location of the neurons with respect to the neuron under consideration. Experiments performed with character images show that the new approach can learn and recognize patterns very effectively. (C) 2003 Elsevier B.V. All rights reserved.
A few of common cases are listed when training pattern pairs may perturb for fuzzy neural network systems. Next, a new concept is proposed which is the sensitivity of a Fuzzy Bidirectional Associative
A few of common cases are listed when training pattern pairs may perturb for fuzzy neural network systems. Next, a new concept is proposed which is the sensitivity of a Fuzzy Bidirectional Associative
K-Means algorithm hardly attains higher accuracy for sparsely distributed samples. While a nonlinear separable problem can be changed to a linear (or approximately linear) separable one, by using kern
K-Means algorithm hardly attains higher accuracy for sparsely distributed samples. While a nonlinear separable problem can be changed to a linear (or approximately linear) separable one, by using kern
A learning-based control approach is presented for force servoing of a robot with vision in an unknown environment. Firstly, mapping relationships between image features of the servoing object and the joint angles of ...
详细信息
A learning-based control approach is presented for force servoing of a robot with vision in an unknown environment. Firstly, mapping relationships between image features of the servoing object and the joint angles of the robot are derived and learned by a neural network. Secondly, a learning controller based on the neural network is designed for the robot to trace the object. Thirdly, a discrete time impedance control law is obtained for the force servoing of the robot, the on-line learning algorithms for three neural networks are developed to adjust the impedance parameters of the robot in the unknown environment. Lastly, wiping experiments are carried out by using a 6 DOF industrial robot with a CCD camera and a force/torque sensor in its end effector, and the experimental results confirm the effecti veness of the approach.
暂无评论