| Scheffer, T., Wrobel, S.: A sequential sampling algorithm for a general class of utility criteria. In: Knowledge Discovery and Data Mining. (2000) 330--334 |
....Web, as there is no central database server. Scalability has always been a major concern for ILP algorithms. With the expected growth of the Semantic Web, this problem increases as well. Therefore, the performance of the mining algorithms has to be improved, e.g. by sampling (see for instance [41]) As for the problem of distributed data, it is a challenging research topic to develop algorithms which can perform the mining in a distributed manner, so that only (intermediate) results have to be transmitted, and not whole datasets. 5.2 Semantic Web Usage Mining Usage mining can also be ....
Tobias Scheffer and Stefan Wrobel. A sequential sampling algorithm for a general class of utility criteria. In Knowledge Discovery and Data Mining, pages 330-334, 2000.
....05 The first factor weights the size of ext(h) in relation to the samples size and the second factor compares the distribution in ext(h) with that of the overall population. A theoretical investigation of quality functions as this one and its distinction from averaging functions can be found in [16]. Here, we identify the data set with the overall population and consider ext(h) a sample. The significance of a difference in the distribution is determined with respect to the null hypothesis. In fact, additional rules are found that cover some of the previously uncovered instances: h 6 : ....
Tobias Scheffer and Stefan Wrobel. A Sequential Sampling Algorithm for a General Class of Utility Criteria. In Proceedings of the International Conference on Knowledge Discovery and Data Mining, 2000.
No context found.
T. Scheffer and S. Wrobel. A sequential sampling algorithm for a general class of utility functions. In Proceedings of the International Conference on Knowledge Discovery and Data Mining, 2000.
No context found.
Scheffer, T., Wrobel, S.: A sequential sampling algorithm for a general class of utility criteria. In: Knowledge Discovery and Data Mining. (2000) 330--334
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC