A feedforward control based on neural networks to attenuate the effect of external vibrations on the positioning accuracy of hard disk drives (HDDs) is presented. The adaptive neural network compensator utilises accelerometer signals to detect external vibrations. No information on the plant, sensor and disturbance dynamics is needed in the design of the adaptive neural network compensator. The...

Multi-motor synchronous system is a multi-input multi-output, nonlinear and high coupling control system. The neural network generalized inverse system can realize the linearization and decoupling of the nonlinear control. Local minima, irrationality learning rate and over learning easily occur in traditional feedforward neural networks. To overcome the problems, it put forward a single hidden-...

This paper considers a batch gradient method with penalty for training feedforward neural networks. The role of the penalty term is to control the magnitude of the weights and to improve the generalization performance of the network. An usual penalty is considered, which is a term proportional to the norm of the weights. The boundedness of the weights of the network is proved. The boundedness i...

We propose an initialization method for feedforward artificial neural networks (FFANNs) trained to model physical systems. A polynomial solution of the physical system is obtained using a mathematical model and then mapped into the neural network to initialize its weights. The network can next be trained with a dataset to refine its accuracy. We focus attention on an elliptical partial differen...

This paper describes an evolutionary neural network approach to Hang Seng stock index forecast. In this approach, a feedforward neural network is evolved using an evolutionary programming algorithm. Both the weights and architectures (i.e., connectivity of the network) are evolved in the same evolutionary process. The network may grow as well as shrink. The experimental results show that the ev...

Face recognition is one of the most important image processing research topics which is widely used in personal identification, verification and security applications. In this paper, a face recognition system, based on the principal component analysis (PCA) and the feedforward neural network is developed. The system consists of two phases which are the PCA preprocessing phase, and the neural ne...

The supervised training of feedforward neural networks is often based on the error backpropagation algorithm. The authors consider the successive layers of a feedforward neural network as the stages of a pipeline which is used to improve the efficiency of the parallel algorithm. A simple placement rule is used to take advantage of simultaneous executions of the calculations on each layer of the...

This paper rigorously establishes thut standard rnultiluyer feedforward networks with as f&v us one hidden layer using arbitrary squashing functions ure capable of upproximating uny Bore1 measurable function from one finite dimensional space to another to any desired degree of uccuracy, provided sujficirntly muny hidden units are available. In this sense, multilayer feedforward networks are u c...

Henson (1996) has argued that several results including fillin effects, patterns of protrusions and performance on lists of alternating similar and dissimilar items (the sandwich effect) preclude a model of serial recall that relies on chaining associations between items. However, this conclusion is at odds with other data showing that serial recall improves dramatically when study lists approx...