Answer Happy

Below we have provided a training dataset consisting of two data samples. Assume an augmented linear regression model along with a learning rate of n = 0.05. Calculate the value of 0 after one gradient descent update step. Note: In this linear regression model 00 corresponds to the bias term. Assume the following setting for this problem - 0 [4, -2,-4, 8] = The two data samples are: x1 = [2, 1, 2] x2 = [1, 2, 2] The target (true) values for data samples: Y1 = 4 Y2 = 3 You can either calculate one epoch gradient descent update by hand or use the following starter code: import numpy as np X = np.array([[...,2,1,2], [...,1,2,2]]) w = np.array([...]) eta = 0.05 Y=... w = w-eta*np.dot((np. dot(X,w)-Y),X) print (w) Hint: Think about the augmentation process. O [4.25 -6.15 -5.1 1.5] O [4.25 -4.15 -3.1 4.5] O [2.25 -4.15 -3.1 0.5] O [3.25 -3.15 -5.1 6.5]