MCS
2004
Springer
14 years 4 months ago
2004
Springer
Abstract. One of the potential advantages of multiple classifier systems is an increased robustness to noise and other imperfections in data. Previous experiments on classificati...
FOCS
2006
IEEE
14 years 5 months ago
2006
IEEE
We address well-studied problems concerning the learnability of parities and halfspaces in the presence of classification noise. Learning of parities under the uniform distributi...