Consider a data set with three examples. For example i, x(i) is the value of the input feature and t(i) is the value of the target. Example x(i) t(i) 1 1 0 2 2 4 3 3 1 Table 1: Data Set for Linear Regression We will fit a ridge regression model to the data above resulting in on weight w and one bias term b. Recall that in vector notation (with the bias term incorporated into the design matrix via concatenation into a vector of all 1s), this corresponds to training with: Derive the gradient descent update rule using the parameter values below. w = 2, b = 1, = 0.2 (Learning rate) Assume that the cost function is the total loss over all the training examples. We recommend breaking up the calculations into easy to understand steps rather than only writing down the final answer. We will award partial marks for correct intermediate steps. You should leave your answer in the form of two equations: b b C (1) w w D (2) where A,B,C,D are real valued numbers