3. Suppose a simple single layer perceptron with 2-d input X= (x1, x2), a bias, ReLU for activation function, and MSE (mean squared error) for loss function. D X 2 D D D 13 X: 1 2 0 -1 a. Show evolution of weights according to stochastic gradients algorithm with batch size=1 b. Show evolution of weights according to stochastic gradients algorithm with batch size=2