Suppose the domain X is the real line, R, and the labels lie in Y = {- 1,1}, Let C be the concept class consisting of simple threshold functions of the form be for some 9 E R, where h9(x) = -1 for all x s 9 and he [x] = 1 otherwise. Give a simple and efficient PAC learning algorithm for C that uses only _ 1 l m _ 0( 6 log 5 ) training examples to output a classifier with error at most 8 with probability at least 1 6