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.
Building language models for source code enables a large set of improvements on traditional software engineering tasks. One promising application is automatic code completion. State-of-the-art techniques capture code regularities at token level with lexical information. Such language models are more suitable for predicting short token sequences, but become less effective with respect to long statement...
Formal program verification is a powerful technique to ensure the correctness of programs. To perform this technique, one oftentimes needs to manually specify assertions, which is a time-consuming and error-prone task. Generating assertions automatically can significantly improve the usability of formal program verification. To decide where an assertion is needed heavily and which value range of the...
Dynamic timing errors (DTEs), that are caused by the timing violations of sensitized critical timing paths, have emerged as an important threat to the reliability of digital circuits. Existing approaches model the DTEs without considering the impact of input operands on dynamic path sensitization, resulting in loss of accuracy. The diversity of input operands leads to complex path sensitization behaviors,...
This paper analyses the deficiency of SVM-RFE feature selection algorithm and puts forward a new feature selection method combined with SVM-RFE and PCA. Firstly, we get the optimal feature subset through the method of cross validation based on SVM-RFE. Then, we use the PCA method to analyse the main component about optimal feature subset and get a lower-dimension and independent data sets which are...
The traditional determination method of K/S value is testing the CIEL*a*b* value of each dyeing fabric fistly by the color chromatic aberration SC-80, and then, based on the CIEL*a*b* value, they calculate the K/S value scoping 10 nm within 400 nm-700 nm the visible region. These are finished with the help of the software Hyper Choshoku-Senka TX.The RBF neural network is used in this paper to estimate...
Based on analyzing fundamental principle of Back Propagation Network Model, in view of the limitations of BP algorithm, this paper proposed the homologous improved-algorithm from the two aspects of quickening the BP learning speed and raising the degree of convergence. In the course of the complex water flood development, the paper, considering the adaptability feature of the different random factors...
Forecast model of the nitrobenzene compound biological toxicity has been established based on the RBF neural network, the correlation coefficient between the predicted value and the actual value reaches 0.993. Prediction errorpsilas biggest absolute value is 0.34, the rest is under 0.20.So it is a good forecast mode of the nitrobenzene compound biological activity.
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.