Consider the class C of concepts of the form: (aa ≤ xx1 ≤ bb) ᴧ (cc ≤ xx2 ≤ dd). Note that each concept in this class corresponds to a rectangle in 2-dimensions. Let a, b be integers in the range [0, 199] and c, d be integers in the range [0, 99]. Give an upper bound on the number of training examples sufficient to assure that for any target concept c Є C, any consistent learner using H = C will, with probability 0.99, output a hypothesis with error at most 0.05.