Aimed at the inadequacy of the standard bp algorithm, a near optimal learning rate bp algorithm (NOLRbp) is presented. Selecting the learning rate of the algorithm based on one-dimensional search algorithm of optimiza...
详细信息
ISBN:
(纸本)9783037852828
Aimed at the inadequacy of the standard bp algorithm, a near optimal learning rate bp algorithm (NOLRbp) is presented. Selecting the learning rate of the algorithm based on one-dimensional search algorithm of optimization theory avoids the blindness in determining the learning rate. Simulations show that the algorithm is superior to the standard bp algorithm (SDbp), momentum bp algorithm (MObp) and variable learning rate bp algorithm (VLbp).
Teaching quality evaluation is an important link in the field of education, which not only relates to the improvement of teachers' teaching and students' learning effect, but also directly affects the reputati...
详细信息
This paper takes a kind of ceramic glaze as an example, and builds an improved bp neural network model for optimizing the formulation on ceramic glaze. The improved bp neural network adopts Levenberg- Marquardt algori...
详细信息
ISBN:
(纸本)9781612848372
This paper takes a kind of ceramic glaze as an example, and builds an improved bp neural network model for optimizing the formulation on ceramic glaze. The improved bp neural network adopts Levenberg- Marquardt algorithms. The paper reviews how to build the ceramic formulation optimization model based on bp artificial neural network, including the establishment of neural network, the training, and the inspection of results. Meanwhile, the software Matlab7 has a neural network toolbox. The bp network model of ceramic formulation optimization is simulated by Matlab7. The model has achieved the good effect in the prediction precision and the algorithm convergence speed respects. So, application of improved bp algorithm has an important significance on ceramic formulation optimization research.
Software defect is an important indicator to evaluate software product quality. To reduce the defects of software products and to improve the quality of software is always the goal of software development. This paper ...
详细信息
ISBN:
(纸本)9781728181172
Software defect is an important indicator to evaluate software product quality. To reduce the defects of software products and to improve the quality of software is always the goal of software development. This paper combines the simulated annealing (SA) algorithm and JCUDA technology to improve the bp algorithm, to build an improved software defect prediction model with higher prediction accuracy. The experimental results show that the software defect prediction model based on improved bp algorithm is able to accurately predict the software defects, which is better than the traditional bp algorithm.
This paper describes the digital character recognition process and steps. Using artificial neural networks with momentum term and adaptive learning rate back-propagation algorithm to train and identify the ideal signa...
详细信息
ISBN:
(纸本)9783642233203
This paper describes the digital character recognition process and steps. Using artificial neural networks with momentum term and adaptive learning rate back-propagation algorithm to train and identify the ideal signal and noise signal containing the number of characters. By comparing the results to obtain that using the same network with the ideal signal and noise signal for training the network, the system can be more fault-tolerant.
The current control method based on double hysteresis current control and space vector is taken, so that the current tracing control of three phase VSR can realized. The predictive current control based on bp algorith...
详细信息
ISBN:
(纸本)9783037859391
The current control method based on double hysteresis current control and space vector is taken, so that the current tracing control of three phase VSR can realized. The predictive current control based on bp algorithm is presented, and the drawback that there is beat during the control of SVPWM based on hysteresis can be made up, which has serious influence on the current tracing when the difference value changed violently. Without the rise of sampling frequency, the reference offset current of next time is predicted using of historical current. The simulation results show that the predictive current control based on bp algorithm is correct and valid. The deadbeat control of SVPWM based on hysteresis is realized, less harmonic current and better tracing are got.
bp algorithm was used to forecast the mine water quantity of Qiupigou coal mine as instance. The influencing factors for the mine water quantity were analyzed first. Based on the historical data, mining age, mining de...
详细信息
ISBN:
(纸本)9783037855508
bp algorithm was used to forecast the mine water quantity of Qiupigou coal mine as instance. The influencing factors for the mine water quantity were analyzed first. Based on the historical data, mining age, mining depth, rainfall of the year and rainfall in the last year affected the mine water quantity of Qipigou. The network model of mine water including three layers was established. Input layer includes four neurons, middle layer is six and output layer is one. The network model is trained by historical data from 1988 to 2007. The training make the network model get acquainted the realistic relationship between the influencing factors and mine water quantity. The forecast results show that the error of the network is under 8%, the minimum value of mine water quantities from 2011 to 2025 in Qiupigou mine is 704m(3)/h and the maximum value is 860m(3)/h.
First, the paper anylizes the standard bp algorithm. Toward the limitation of the standard bp alogrithm, an improved bp alogrithm is obtained by modifying the action function, regulating the learning rate and choosing...
详细信息
ISBN:
(纸本)9780769536996
First, the paper anylizes the standard bp algorithm. Toward the limitation of the standard bp alogrithm, an improved bp alogrithm is obtained by modifying the action function, regulating the learning rate and choosing the initial weights. And then a recognition example about license plate recognition technology is given to prove the improved bp algorithm. From the exam results, the improved bp algorithm has some advantages in fast convergence speed, short recognition time and high recognition rate.
It is not satisfied with the increasing need day to day that the conventional digital image processing arithmetic. The bp neural network is one of the most effective means with the merits such as parallel computation,...
详细信息
ISBN:
(纸本)9781424409723
It is not satisfied with the increasing need day to day that the conventional digital image processing arithmetic. The bp neural network is one of the most effective means with the merits such as parallel computation, nonlinear mapping and the self-adaptation;ARM (Advanced RISC Machines) microcontroller is widely used in lots of fields with characteristics of high-performance, small volume, low power dissipation and low-cost exactly. This paper researches on coal gangue on-line automatic separation system based on the improved bp algorithm and ARM. First, the general system is introduced in brief. Then, it is the basal information on the bp neural network and the digital image processing arithmetic. It is emphasized that the digital image processing;is applied with the improved bp algorithm. After then the design of the interface circuits is in detail discussed find the ARM microcontroller and last the emulation debugging figures are given. Experiments show that the design is successful. A newly means, which automatically select the gangue from the coal, is explored.
Based on JS engine, this paper made a detailed analysis on the standard bp algorithm, bp algorithm with additional momentum item, bp algorithm of parameter to adjust and bp network based on LM algorithm. Finally, this...
详细信息
ISBN:
(纸本)9783037852989
Based on JS engine, this paper made a detailed analysis on the standard bp algorithm, bp algorithm with additional momentum item, bp algorithm of parameter to adjust and bp network based on LM algorithm. Finally, this paper gets the optimization algorithm and network by comparing in training step and diagnostic accuracy. In the end, the front panel of the diagnosis system is designed by MATLAB graphical user interface.
暂无评论