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.
In this paper, two different types of neural networks are investigated and employed for the online solution of strictly-convex quadratic minimization; i.e., a two-layer back-propagation neural network (BPNN) and a discrete-time Hopfield-type neural network (HNN). As simplified models, their error-functions could be defined directly as the quadratic objective function, from which we further derive...
BP neutral network and its improved algorithms are applied to compensate sensor's performance. The defects of BP, for example, converging slowly, being easy to converge to minimum of one part are improved efficiently. Training programs are done. Results show that the performance of sensor is improved highly. Network has a high converging speed and good precision. The correction precision increases...
Based on the fuzzy classifying approach, the paper puts forwards a diagnosis algorithm of Back-propagation Neural Network. For some complexity environments, the traditional Back- propagation Neural Network has some limitations on classification. The paper applies fuzzy model on Neural Network structure, by using classifying variance and energy function to adjust the convergence of the Neural Network...
In this paper, a Dmeyer wavelet function is utilized to decompose the mixed load current waveforms and extract the parameter values which represent the nonlinear loads. A three layer BP neural network model is established, which is trained using Levenberg-Marquardt (LM) algorithm which shows fast convergence and strong stability. The results indicate that the proposed method of the wavelet BP neural...
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.