The key theorem of learning theory with samples corrupted by zero-expect noise on chance space.
Jun-Hua LiHai-Jun LiQiang HePublished in: ICMLC (2012)
Keyphrases
- learning theory
- noise free
- computational learning theory
- reproducing kernel hilbert space
- instructional design
- additive gaussian noise
- data sets
- pac learning
- noise reduction
- concept classes
- theoretical computer science
- learning theories
- training set
- automata theory
- median filter
- machine learning algorithms
- concept class
- database
- salt pepper