Gradient checking quiz

April 15, 2014 2 Comments

Let J(\theta) = \theta^3. Furthermore, let \theta = 1 and \epsilon=0.01. You use the formula

(J(\theta+\epsilon )- J(\theta-\epsilon))/2\epsilon

to approximate the derivative. What value do you get using this approximation ?(When \theta=1,the true, exact derivative is
d/d\theta J(\theta) = 3 ).

The Octave code that I used to solve this is 

((1+0.01)^3-(1-0.01)^3)/(2*0.10)

3.0001

Filed under Machine Learning

2 Responses to Gradient checking quiz

  1. suggestion says:
    January 24, 2018 at 5:37 am

    (2*0.10) it should be 2*0.01

    Reply

Leave a Reply

Fill in your details below or click an icon to log in:

Gravatar
WordPress.com Logo

You are commenting using your WordPress.com account. ( Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. ( Log Out /  Change )

Cancel

Connecting to %s

%d bloggers like this: