Consider the AdaBoost algorithm summarized in the textbook and discussed in class. Recall that this algorithm updates weights for each training example in response to how accurately the base (weak) classifier performed on this example in the previous iteration. Suppose that we start with a uniform weight distribution for 20 data points (each point is weighted 0.05). Describe how the weights will be adjusted after one iteration of AdaBoost if the weak classifier is a weighted Majority Classifier. In this example, 18 examples belong to the positive class and 2 examples belong to the negative class.

the benefits of raising bc’s minimum wage to $15 through a

series of pre-announced staged increases far outweigh the likely

costs. claims that such an increase will lead to massive job losses

in low-wage sectors of the economy are not credible.

• an increase to $15 would result in some job losses. however,

the likely impact is less than a 1 per cent reduction in the overall

provincial employment rate, and a 7.6 per cent reduction in the

employment rate for those currently making between $10.25

and $15 per hour.

• the large job loss impacts predicted by some opponents of

minimum wages misrepresent the existing economic research. in

reading and using that research, it is important to recognize that

estimates showing job loss effects of minimum wage increases

apply only to teenagers. estimated effects for young adult and

adult workers range from insignificant to non-existent.

• focusing on teenage workers plays up an inaccurate stereotype

about who earns very low wages in bc and leads to exaggerated

claims about job losses. only 26 per cent of those currently making

between $10.25 and $12 are teenagers, and only 5 per cent

of those making between $12 and $15 are teenagers.