Title :
The Key Theorem of Learning Theory with Samples Corrupted by Equality-Expect Noise on Quasi-Probability Space
Author :
Ha, Ming-Hu ; Du, Er-ling ; Feng, Zhi-fang ; Bai, Yun-Chao
Author_Institution :
Coll. of Math. & Comput. Sci., Hebei Univ., Baoding
Abstract :
Based on statistical learning theory on probability space and good properties of quasi-probability, some important inequalities are proven on quasi-probability space in this paper. Furthermore, some new concepts of learning theory are given and the key theorem of statistical learning theory is given and proven when samples are corrupted by equality-expect noise on quasi-probability space
Keywords :
learning (artificial intelligence); probability; statistical analysis; equality-expect noise; quasiprobability space; statistical learning theory; Additives; Chebyshev approximation; Cybernetics; Density functional theory; Distribution functions; Educational institutions; Machine learning; Mathematics; Probability; Random variables; Statistical learning; Quasi-probability; equality-expect noise; the empirical risk functional; the expected risk functional; the key theorem;
Conference_Titel :
Machine Learning and Cybernetics, 2006 International Conference on
Conference_Location :
Dalian, China
Print_ISBN :
1-4244-0061-9
DOI :
10.1109/ICMLC.2006.258981
