Narrow Results

This paper presents a fast Neural Network algorithm, in which the step is regarded as the function of the error and the output function of network node, and weight is calculated by different step. By adopting the fast NN algorithm, we developed a speaker-independent speech recognition system. The experiment shows that the new algorithm is over 10 times faster than the traditional BP algorithm and has better performance and spreading ability.

Binarization of gray scale document images is one of the most important steps in automatic document image processing. In this paper, we present a two-stage document image binarization approach, which includes a top-down region-based binarization at the first stage and a neural network based binarization technique for the problematic blocks at the second stage after a feedback checking. Our two-stage approach is particularly effective for binarizing text images of highlighted or marked text. The region-based binarization method is fast and suitable for processing large document images. However, the block effect and regional edge noise are two unavoidable problems resulting in poor character segmentation and recognition. The neural network based classifier can achieve good performance in two-class classification problem such as the binarization of gray level document images. However, it is computationally costly. In our two-stage binarization approach, the feedback criteria are employed to keep the well binarized blocks from the first stage binarization and to re-binarize the problematic blocks at the second stage using the neural network binarizer to improve the character segmentation quality. Experimental results on a number of document images show that our two-stage binarization approach performs better than the single-stage binarization techniques tested in terms of character segmentation quality and computational cost.

The paper proposes a dynamics model basing on the BP algorithm. The control scheme is an efficient combination of a computed-torque control and a neural network as a compensation structure, which enhances the adaptability of controller. Though there are errors during the modeling for the robot dynamics, they can be compensated according to the rule of adjusting weight values. The controller has obtained the ideal result both in theory and in experiment.

A Legendre wavelets neural network is constructed with Legendre wavelets based on BP neural network. Because of the piece wise expression and being polynomials features which Legendre wavelets defined on the interval [0,1) has, the Legendre wavelets neural network has the advantages of simple structure and high convergence rate. Trained by BP algorithm, a better approximate result is obtained by using Legendre wavelets neural network with six wavelet basis functions to approximate one function.

As a product of market economy, the stock market has its characteristics of high stakes and attractive benefits. But the fluctuation of stock price is always affected by many complexity factors. In this paper, China Merchants Bank stock is chosen as an example in utilizing good classification capability of BP neural network to forecast its future trend. In addition, the accuracy and stability of four kinds of neural networks in prediction of stock market trend are analyzed. Simulation experiments show that BP neural network has better performance than other approaches in learning capacity and generalization.