Question 5 [4 pts]: Assuming we have six instances, which belong to two classes: Ci={(1,-1), (1, 1). (0.-1)} and C;={(0.1).(-1,0). (-1,-1)}. Each instance has two features. Assuming the class lable for Ci and C2 are 1 and 0, respectively. The learning rate n=0.1, and the initial weights are wa=0.5, wi=0.5, and wz=0.5 (where w=0.5 is the weight value for bias). Please use Delta rule (AdaLine: Adaptive Linear Elements) to train a perceptron (i.e., linear decision surface) for these two classes. . Please sequentially select instances from C and C, and list the weight updating of the six instances in the following table [2 pts] Draw six instances in a two dimensional space plot, and also draw the learned decision surface (after passing through all six instances) on the same plot. [2 pts] Weight Desired Actual AW New Weight Input (1,1,-1) (1,1,1) (1,0,-1) (1,0,1) (1,-1,0) (1,-1,-1) Question 5 [4 pts]: Assuming we have six instances, which belong to two classes: Ci={(1,-1), (1, 1). (0.-1)} and C;={(0.1).(-1,0). (-1,-1)}. Each instance has two features. Assuming the class lable for Ci and C2 are 1 and 0, respectively. The learning rate n=0.1, and the initial weights are wa=0.5, wi=0.5, and wz=0.5 (where w=0.5 is the weight value for bias). Please use Delta rule (AdaLine: Adaptive Linear Elements) to train a perceptron (i.e., linear decision surface) for these two classes. . Please sequentially select instances from C and C, and list the weight updating of the six instances in the following table [2 pts] Draw six instances in a two dimensional space plot, and also draw the learned decision surface (after passing through all six instances) on the same plot. [2 pts] Weight Desired Actual AW New Weight Input (1,1,-1) (1,1,1) (1,0,-1) (1,0,1) (1,-1,0) (1,-1,-1)