[SOLVED] DeepLearning HW2

1. Your task is to find a linear approximation of the function 1 + x, x ∈ [0,1]. Your homework should contain the following steps:
2. Generate N = 10000 random numbers from [0,1]:

x₁,x₂,…,x_N ∈ [0,1],

√

and then obtain their labels: y_i =             1 + x_i, i = 1,2,…,N.

1. Do linear regression on your generated data using stochastic gradient descent (implement yourself).
2. Do linear regression on your generated data using mini-batch gradient descent (implement yourself). d*) Do linear regression on your generated data using tensorflow.
3. Sketch the graphs of all approximations on one graph.
4. Compare all solutions with the first degree Taylor approximation of√

the function      1 + x.

2*. Pass the following tutorial.