The paper is proposed for fuzzy neural net based on genetic algorithm adjusting asynchronous motor direct torque control system. Fuzzy neural network training usually adopts the back-propagation study algorithm (bp) Y...
详细信息
ISBN:
(纸本)0780378652
The paper is proposed for fuzzy neural net based on genetic algorithm adjusting asynchronous motor direct torque control system. Fuzzy neural network training usually adopts the back-propagation study algorithm (bp) Yet the training time of bp algorithm is longer and it is easy to fail into the problems such as local minima and so on. Adopt the genetic algorithm to optimize with weight of fuzzy neural network and parameters of membership function. Make up for the defect that fuzzy neural network adopts bp algorithm. Make the speed of arithmetic faster. Achieve global optimization.
Generalization ability of the network and training time are the two important aspects that we must consider when we design the neural network algorithms. At the same time, the optimization of neural network architectu...
详细信息
ISBN:
(纸本)0780378652
Generalization ability of the network and training time are the two important aspects that we must consider when we design the neural network algorithms. At the same time, the optimization of neural network architecture must be considered in each artificial neural network based on the bp algorithm. But to the larger networks, there are no more suitable ways to solve this problem. This paper proposes an especial two-hidden-layer artificial neural network. After describing the major steps of this algorithm, some experimental results and analysis are given out. Those experimental results indicate that the generalization ability, training time and the architecture optimization of the networks have been improved obviously in this algorithm.
A kind of second order algorithm--recursive approximate Newton algorithm was given by Karayiannis. The algorithm was simplified when it was formulated. Especially, the simplification to matrix Hessian was very reluct...
详细信息
A kind of second order algorithm--recursive approximate Newton algorithm was given by Karayiannis. The algorithm was simplified when it was formulated. Especially, the simplification to matrix Hessian was very reluctant, which led to the loss of valuable information and affected performance of the algorithm to certain extent. For multi layer feed forward neural networks, the second order back propagation recursive algorithm based generalized cost criteria was proposed. It is proved that it is equivalent to Newton recursive algorithm and has a second order convergent rate. The performance and application prospect are analyzed. Lots of simulation experiments indicate that the calculation of the new algorithm is almost equivalent to the recursive least square multiple algorithm. The algorithm and selection of networks parameters are significant and the performance is more excellent than bp algorithm and the second order learning algorithm that was given by Karayiannis.
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...
详细信息
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.
No lossless data compression method based on neural network is found before. A lossless compression method based on bp network for the long character-string of 0 and 1 is given by establishing specifi
No lossless data compression method based on neural network is found before. A lossless compression method based on bp network for the long character-string of 0 and 1 is given by establishing specifi
We present a modeling method of the Nonlinear Dynamic System Nerve Network Based on tne unaouc time series in this paper and put forward a new *** last,A case study on modeling of the chaotic time series was performed.
We present a modeling method of the Nonlinear Dynamic System Nerve Network Based on tne unaouc time series in this paper and put forward a new *** last,A case study on modeling of the chaotic time series was performed.
We developed a GA-bp algorithm by combining the genetic algorithm (GA) with the back propagation (bp) algorithm and established a genetic bp neural network. We also applied the bp neural network based on the bp algori...
详细信息
We developed a GA-bp algorithm by combining the genetic algorithm (GA) with the back propagation (bp) algorithm and established a genetic bp neural network. We also applied the bp neural network based on the bp algorithm and the genetic bp neural network based on the GA-bp algorithm to discriminate earthquakes and explosions. The obtained result shows that the discriminating performance of the genetic bp network is slightly better than that of the bp network.
The back propagation (bp) model of artificial neural networks (ANN) has many good qualities comparing with ordinary methods in land suitability *** analyzing ordinary methods’ limitations,some sticking points of bp m...
详细信息
The back propagation (bp) model of artificial neural networks (ANN) has many good qualities comparing with ordinary methods in land suitability *** analyzing ordinary methods’ limitations,some sticking points of bp model used in land evaluation,such as network structure,learning algorithm,etc.,are discussed in detail,The land evaluation of Qionghai city is used as a case *** comprehensive assessment method was also employed in this evaluation for validating and comparing.
Based on the simple feature extraction, the neural network is trained by inputting ideal and noisy samples, and the modified bp algorithm is applied to recognize, the 26 English alphabets and the 10 digits, which incr...
详细信息
ISBN:
(纸本)7560317685
Based on the simple feature extraction, the neural network is trained by inputting ideal and noisy samples, and the modified bp algorithm is applied to recognize, the 26 English alphabets and the 10 digits, which increases the network's ability to tolerate fault and correctly recognize the characters that contain a mass of noise. The network was trained twice, in order that the network's recognition rate to the ideal characters didn't decline, still had two set of ideal samples as input at the second training, and the output weights of first training were input as initial weights at the second training. In order to obtain the perfect structure parameters of network and research each parameter's effect on the performance of network, a large number of simulation tests were conducted. Finally, recognition rate above 95% was obtained on the condition that the noise's mean was 0.2, and achieved 100% recognition rate to the ideal characters.
The human-computer communication mode is adopted to identify the parts. In the-course of Pattern Recognition, We adopted bp neural network and brings forward a sort of improved bp algorithm based on the limitation of ...
详细信息
ISBN:
(纸本)7560317685
The human-computer communication mode is adopted to identify the parts. In the-course of Pattern Recognition, We adopted bp neural network and brings forward a sort of improved bp algorithm based on the limitation of the bp algorithm. When the bp neural network algorithm is applied for identification of industrial parts, the speed and accuracy of identification is improved greatly. The practices indicate that this system can increase productivity and guarantee the quality of products.
暂无评论