Machine Learning

10-601, Fall 2012

Carnegie Mellon University

Tom Mitchell and Ziv Bar-Joseph

Homework 1: pdf, code.
Due Friday, Sept. 14 at 4pm, in Sharon Cavlovich's office (GHC 8215). HW1 solutions.

Homework 2: pdf, data.
Due Friday, Sept. 28 at 4pm, in Sharon Cavlovich's office (GHC 8215). HW2 solutions.

To submit your code, send an email to with the subject:"yourandrewid-HW2-Code" by 28 September, 4 pm. Include *only* your code.

Homework 3: pdf.
Due Monday, Oct. 15 at 4pm, in Sharon Cavlovich's office (GHC 8215). HW3 solutions.

Homework 4: pdf, data.
Last modified: 11/06/2012 12:14pm
Due Friday, Nov. 9 at 4pm, in Sharon Cavlovich's office (GHC 8215). HW4 solutions

To submit your code, send an email to with the subject:"yourandrewid-HW4-Code" by Nov. 9, 4 pm. Include *only* your code.

Homework 5: pdf, code.
Due Friday, Nov 30 at 4pm, at Sharon's office. See pdf for AFS code submission. HW5 solutions

Update 12/15: the final exam average was 68.7, std dev 12.
Update 12/7: Aggregate statistics of average grades on homeworks 1-4, for people enrolled in the course:

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  45.52   73.44   82.93   80.38   88.80   96.50 
The formula to compute one person's average grade is just a simple average of all the homeworks (with rescaling to 100 for each): (hw1*100/51 + hw2 + hw3*100/75 + hw4) / 4

These statistics are not final but may give a helpful rough picture of things.

Also: Midterm solutions and statistics.

(update 10/24): Current aggregate statistics as of HW1, HW2, and the midterm. Histogram. Quantiles:
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  6.707  63.810  70.800  69.980  78.760  93.200 
To calculate this for yourself: (1) multiply HW1 grade by 100/51; (2) score = .08/Z*HW1 + .08/Z*HW2 + .25/Z*Midterm, where Z=.08+.08+.25.
Final solutions.


Note - We might reuse problem set questions from previous years, covered by papers and webpages, we expect the students not to copy, refer to, or look at the solutions in preparing their answers. Since this is a graduate class, we expect students to want to learn and not google for answers.

Collaboration policy - Homeworks must be done individually, except where otherwise noted in the assignments. 'Individually' means each student must hand in their own answers, and each student must write their own code in the programming part of the assignment. It is acceptable, however, for students to collaborate in figuring out answers and helping each other solve the problems. We will be assuming that, as participants in a graduate course, you will be taking the responsibility to make sure you personally understand the solution to any work arising from such a collaboration.

Late homework policy -
  • Late homeworks will be penalized according to the following policy:
    • Homework is worth full credit at the time it is due.
    • It is worth half credit for the next 48 hours.
    • It is worth zero credit after that.
  • Turn in hardcopies of all late homework assignments to Sharon Cavlovich. Put down the date and time of submission on the HW sheets when submitting your assignments to Sharon. If she is not available, please slide your HW under her door.