Title :
The key theorem of learning theory about examples corrupted by noise
Author :
Ha, Ming-Hu ; Li, Jun-Hua ; Li, Jia ; Wang, Xi-Zhao
Author_Institution :
Coll. of Math. & Comput. Sci., Hebei Univ., Baoding, China
Abstract :
Statistical learning theory has investigated the conditions for consistency of the learning processes based on the empirical risk minimization induction principle. However, it deals with the unrealistic, i.e. noise-free case. We give the key theorem when the outputs are corrupted by noise.
Keywords :
learning (artificial intelligence); minimisation; random noise; statistical analysis; empirical risk minimization induction principle; learning processes; noise corruption; statistical learning theory; Convergence; Cybernetics; Educational institutions; Machine learning; Probability distribution; Random variables; Risk management; Statistical learning; Sufficient conditions;
Conference_Titel :
Machine Learning and Cybernetics, 2004. Proceedings of 2004 International Conference on
Print_ISBN :
0-7803-8403-2
DOI :
10.1109/ICMLC.2004.1382091
