Consider the classification problem defined below. {p_1=[(2 2)],t_1=0} {p_2=[(1 -2)],t_2=1} {p_3=[(-2 2)],t_3=0} {p_4=[(

[answerhappygod]

Consider the classification problem defined below.
{p_1=[(2 2)],t_1=0} {p_2=[(1 -2)],t_2=1} {p_3=[(-2 2)],t_3=0} {p_4=[(-1 1)],t_4=1}
Use the following initial weights and biase:
W(0)=[(0&0)] b(0) = 0
Solve the classification problem with the perceptron rule. Apply each input vector in order, for as many repetitions as it takes to ensure that the problem is solved.
2. Draw a graph of the training data and the decision boundary for Problem 1.
3. We have a classification problem with four classes of input vector. Train a perceptron network to solve this problem using the perceptron learning rule. The training set is as follows:
{p_1=[(1 1)],t_1=[(0 0)]} {p_2=[(1 2)],t_2=[(0 0)]} {p_3=[(2 -1)],t_3=[(0 1)]}
{p_4=[(2 0)],t_4=[(0 1)]} {p_5=[(-1 2)],t_5=[(1 0)]} {p_6=[(-2 1)],t_6=[(1 0)]}
{p_7=[(-1 -1)],t_7=[(1 1)]} {p_8=[(-2 -2)],t_8=[(1 1)]}
Use the following initial weights and biases:
W(0)=[(1&0 0&1)] b(0)=[(1 1)]