KEMBAR78
Quiz Machine Learning | PDF | Test Set | Theoretical Computer Science
Scribd
Upload
190 views4 pages

Quiz Machine Learning

This document contains an assignment on linear regression and gradient descent. It provides a sample training set with 4 examples to predict a student's second year GPA based on their first year GPA. It then asks 5 exercises regarding properties of linear regression and gradient descent: 1) the number of training examples is 4, 2) the cost function J(0,1) for the training set, 3) the predicted value for an input of 6, 4) true statements about gradient descent, and 5) implications if the cost function was minimized to 0 on the training set.

Uploaded by

Matt
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
190 views4 pages

Quiz Machine Learning

This document contains an assignment on linear regression and gradient descent. It provides a sample training set with 4 examples to predict a student's second year GPA based on their first year GPA. It then asks 5 exercises regarding properties of linear regression and gradient descent: 1) the number of training examples is 4, 2) the cost function J(0,1) for the training set, 3) the predicted value for an input of 6, 4) true statements about gradient descent, and 5) implications if the cost function was minimized to 0 on the training set.

Uploaded by

Matt
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

24/01/14

Advanced Algorithms
Floriano Zini
Free University of Bozen-Bolzano
Faculty of Computer Science
Academic Year 2013-2014

Lab 12 Linear regression


and gradient descent

24/01/14

Assignment 10
Exercise 1
Consider the problem of predicting how well students do in their second year of
college/university, given how well they did in their first year. Specifically, let x
be equal to the number of "A" grades (including A-. A and A+ grades) that a
student receives in their first year of college (freshmen year). We would like to
predict the value of y, which we define as the number of "A" grades they get in
their second year (sophomore year).
Exercises 1 through 3 will use the training set on the
right of a small sample of different students
performances. Here each row is one training example.
Recall that in linear regression, our hypothesis is
h(x)=0+1x, and we use m to denote the
number of training examples.

For the given training set, what is the value of m?

Assignment 10
Exercise 2
For this question, continue to assume that we are using the training set given in
the previous slide and let J(0,1) be the cost function as defined in the
lectures. What is J(0,1)?

24/01/14

Assignment 10
Exercise 3
Suppose we set 0=2, 1=0.5. What is h(6)?

Assignment 10
Exercise 4
Let f be some function so that f(0,1) outputs a number. For this problem,
f is some arbitrary/unknown smooth function (not necessarily the cost
function of linear regression, so f may have local optima). Suppose we use
gradient descent to try to minimize f(0,1) as a function of 0 and 1.
Which of the following statements are true? (Check all that apply.)
q Setting the learning rate to be very small is not harmful, and can only
speed up the convergence of gradient descent.
q If 0 and 1 are initialized so that 0=1, then by symmetry (because we
do simultaneous updates to the two parameters), after one iteration of
gradient descent, we will still have 0=1.
q If 0 and 1 are initialized at the global minimum, then one iteration of
gradient descent will not change their values.
q If the first few iterations of gradient descent cause f(0,1) to increase
rather than decrease, then the most likely cause is that we have set the
learning rate to too large a value.

24/01/14

Assignment 10
Exercise 5
Suppose that for some linear regression problem (say, predicting
housing prices as in the lecture), we have some training set, and for
our training set we managed to find some 0, 1 such that J(0,1)=0.
Which of the statements below must then be true? (Check all that
apply.)
q We can perfectly predict the value of y even for new examples that
we have not yet seen. (e.g., we can perfectly predict prices of even
new houses that we have not yet seen.)
q For this to be true, we must have 0=0 and 1=0 so that h(x)=0
q Our training set can be fit perfectly by a straight line, i.e., all of our
training examples lie perfectly on some straight line.
q This is not possible: By the definition of J(0,1), it is not possible for
there to exist 0 and 1 so that J(0,1)=0

You might also like