The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
One of the most significant parameter in increasing the efficiency of MLP NN that utilizes the EBP algorithm for training network is convergence speed which different methods have been proposed for improving it. In this paper, we use a variable learning rate method for increasing the convergence speed of EBP algorithm, which its idea have come from a one way presented to improve the efficiency of...
This paper proposes an ANFIS indoor positioning system based on improved genetic algorithm (GA). In the offline phase, fuzzy rules are abstracted by means of subtractive clustering algorithm with training data, generating the structure of each ANFIS positioning subsystem in X and Y directions. Then each positioning subsystem is trained with improved-GA. In this training algorithm, BP algorithm acts...
This paper presents a novel human-machine interface to control an intelligent wheelchair based on surface electromyography (sEMG) signals. Forehead sEMG signals generated by the facial movements are obtained and analysed by using a CyberLink sensing device. The autoregressive (AR) model is used to extract sEMG features. Then, the BP artificial neural network (BPANN) improved by Levenberg-Marquardt...
The Particle swarm optimizer is intelligent searching in space to find the optimal solutions through the cooperation and competition between particles, being based on the theory of swarm intelligence global optimization algorithm. Its advantage is that simple operation and easy achievement. In this paper, a new algorithm PSO- BP was studied, giving full play to both of the particle swarm algorithm...
Back-Propagation algorithm is one of the most popular algorithms in neural network. But it converges slowly, easily falling into local minima. This paper presents an improved BP algorithm, which can adjust learning rate using golden section method. Based on the algorithm, a diesel engine fault diagnosis system is designed. The simulation results indicate that the algorithm has much faster learning...
Personalized web-based learning has become an important learning form in the 21st century. An earlier research result showed that a fuzzy knowledge extraction model can be established to extract personalized recommendation knowledge by discovering effective learning paths from an access database through an ant colony model. However, critical limitations arose when considering its applications in real...
After studying the disadvantage of BP neural network which has low convergent speed and trap into local minima easily, an idea of designing a new hybrid neural network model. By using Artificial Bee Colony Algorithm (ABC) to expand the updated space of weight and using the fitness functions to decide the better weight. On the basis, make the acquired better value as the weight of BP neural network...
In this paper we proposed a new algorithm for neural network training. This algorithm is developed from modification on Levenberg-Marquardt algorithm for MLP neural network learning. The proposed algorithm has good convergence. This method reduces the amount of oscillation in learning procedure. We named this algorithm as GK-LM Method. An example is given here to show usefulness of this method. Finally...
The feedforward neural networks trained with the online backpropagation (BP) learning algorithm have been widely studied in various areas of scientific research and engineering applications. In this paper we further study the convergence property of the online BP learning algorithm. Unlike the existing convergence analysis mainly focusing on the convergence of the gradient sequence of the error functions,...
In the process of codebook design of vector quantization, traditional LBG algorithm owns the advantage of fast convergence, but it is prone to local optimum and is influenced greatly by initial codebook. Given that the Genetic Algorithm has the capability to produce global optimal results, this paper proposes a new clustering algorithm GA-L based on GA and LBG to improve the quality of codebook. This...
Low convergence accuracy and the acceleration coefficient setting problem have always been the difficult and hot research points of particle swarm optimization algorithm. This paper introduces a composite particle swarm optimization CPSO based on the adaptive PSO and adaptive GA and applies CPSO in the BP network training of turbo-pump fault diagnosis. In addition, the classical test function Rastrigrin...
Through building up the functional relationship between the error E and the learning rate η, we propose one kind of new improved learning rate BP algorithm. This improved BP algorithm adopts serial dynamic adaptive learning rate, thus according to different error E to determine different learning rates. Compared with VLBP, the simulation result shows this improved variable learning rate BP algorithm...
Face recognition is a front complex subject, which involves Physiology, Psychology, Image Processing, Computer Vision, Pattern Recognition and Mathematics. As a research success in the field of wavelet analysis theory, WNN(Wavelet Neural Network), a feed-forward network, avoids the blindness in structure design of BP(Back propagation) neural network, excludes the probability of sub-optimization in...
Injecting weight noise during training has been proposed for almost two decades as a simple technique to improve fault tolerance and generalization of a multilayer perceptron (MLP). However, little has been done regarding their convergence behaviors. Therefore, we presents in this paper the convergence proofs of two of these algorithms for MLPs. One is based on combining injecting multiplicative weight...
Improving fault tolerance of a neural network is an important issue that has been studied for more than two decades. Various algorithms have been proposed in sequel and many of them have succeeded in attaining a fault tolerant neural network. Amongst all, on-line node fault injection-based algorithms are one type of these algorithms. Despite its simple implementation, theoretical analyses on these...
In linear space, the classical perceptron algorithm is simple and practical. But when concerning the nonlinear space it is severely confined mainly on its signal layer structure. This paper analyzes the geometry characteristic of solve region in the pattern set, and presents a new algorithm based on the solve region. The new algorithm could find the better solve vector in the solve region on condition...
This paper makes further research on BP neural network algorithm on the basis of the existing literature. It pointed out the problems in the inherent algorithm, as well as the causes were presented. This research also proposed the BP neural network was difficult to achieve the desired effect when applied to solve the forecasting problems, and then the reasons of that were analyzed, and this point...
The most popular algorithm training feed-forward neural networks is the back-propagation algorithm which minimizes the error function using the steepest descent direction. In practice, although, even with a small learning rate which slows down the training process, the BP algorithm can exhibit oscillatory behavior when it encounters steep valleys. Trust region method has advantages of global convergence...
Estimation of distribution algorithms are increasingly gaining research interest due to their linkage information exploration feature. Two main mechanisms which contribute towards the success of the algorithms are probabilistic modeling and sampling method. Recent attention has been directed towards the development of probabilistic building technique. However, research on the sampling approach is...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.