Title :
The key theorem of learning theory with samples corrupted by zero-expect noise on chance space
Author :
Li, Jun-hua ; Li, Hai-jun ; He, Qiang
Author_Institution :
Coll. of Math. & Comput. Sci., Hebei Univ., Baoding, China
Abstract :
Statistical learning theory has been regarded as one of the best theories for solving the small-sample learning problem on probability space. But it was difficult to deal with the problems on non-probability spaces and it mainly dealt with the noise-free case. In this paper, the key theorem with samples corrupted by zero-expect noise on chance space will be given and proven.
Keywords :
learning (artificial intelligence); probability; chance space; noise-free case; nonprobability spaces; small-sample learning problem; statistical learning theory; zero-expect noise; Abstracts; Erbium; Integrated circuits; World Wide Web; Chance space; Hybrid empirical risk minimization principle; Hybrid variable; Key theorem;
Conference_Titel :
Machine Learning and Cybernetics (ICMLC), 2012 International Conference on
Conference_Location :
Xian
Print_ISBN :
978-1-4673-1484-8
DOI :
10.1109/ICMLC.2012.6359027
