Title :
Partition-based uniform error bounds
Author_Institution :
Dept. of Comput. Sci., California Inst. of Technol., Pasadena, CA, USA
Abstract :
Develops probabilistic bounds on out-of-sample error rates for several classifiers using a single set of in-sample data. The bounds are based on probabilities over partitions of the union of in-sample and out-of-sample data into in-sample and out-of-sample data sets. The bounds apply when in-sample and out-of-sample data are drawn from the same distribution. Partition-based bounds are stronger than VC-type bounds, but they require more computation
Keywords :
learning (artificial intelligence); pattern classification; probability; classifiers; in-sample data; out-of-sample data; out-of-sample error rates; partition-based uniform error bounds; probabilistic bounds; Computer errors; Computer science; Concrete; Error analysis; Injuries; Machine learning; Upper bound; X-ray imaging;
Conference_Titel :
Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4859-1
DOI :
10.1109/IJCNN.1998.685949
