2.6 a. The Hebb rule is sometimes used by converting the binary training patterns (inputs and targets) to bipolar form to find the weight matrix. Apply this procedure to find the weights to store the following classifications: s(1) (1, 0, 1) s(2)= (1, 1, 0) b. Using the binary step function (with threshold 0) as the output unit's activation function, test the response of your network on each of the binary training patterns. c. Using the bipolar step function (with threshold 0) as the output unit's activation function, convert the training patterns to bipolar form and test the network re- sponse again. (1) (2) = 1 - (0, 0, -1) (1, 0, 0) 0 d. Test the response of your network on each of the following noisy versions of the bipolar form of the training patterns: (0, -1, 1) (0, 1, 1) (0, 0, 1) (1, 0, 1) (1, 0, -1) (1, -1, 0) Which of the responses are correct, which are incorrect, and which are indefinite (undetermined)? (0, 1, 0) (0, -1, 0) (1, 1, 0) (1, 1, 1)