Boosting. Theoretical foundations.
•PAC: Probably Approximately
Correct framework
–(e-d) solution
•PAC learning:
–Learning with the pre-specified
accuracy e
and confidence d
–the probability that the
misclassification error is larger than e is smaller
than d
–
–
•Accuracy (e ):
Percent of correctly classified samples in test
•Confidence (d ): The
probability that in one experiment some accuracy will be achieved
•