VS265: Homework assignments Fall2010

Students are encouraged to work in groups, but turn in assignments individually, listing the group members they worked with.

Submission instructions: email both a PDF of your solutions as well as your code (.m or .py files) as attachments to:

   rctn.org vs265 (vs265 should be out front)

You can hand in a paper copy of your solutions before class, but you still have to email your code to the address above before the assignment is due.

Resources

Matlab

Amir, the past GSI for the course says "There is a guide to Matlab on the web by Kevin Murphy which is really excellent. I think it would be great for the VS265 students: http://code.google.com/p/yagtom/"

Python

Fernando Perez at the Brain Imaging Center has an excellent set of resources on Python for scientific computing. You will likely find the "Starter Kit" particularly useful.

Additionally, Josh Bloom (Astronomy) is teaching a Science Research Computing with Python course this semester (on Mondays 2-5pm in Hearst 310, Fall 2010, CCN 06180) which you might want to take. A Python Boot Camp kicked-off that class, and has a lot of accessible introductory material.

Assignments

Lab #1, due Thursday, September 9th at beginning of class

• lab1.pdf
• data.mat

for Python: either ...

  In [1]: import scipy.io
  In [2]: d = scipy.io.loadmat("data.mat")
  In [3]: X,O = d['X'],d['O']

or use data.npz

  In [1]: import numpy as np
  In [2]: d = np.load('data.npz')
  In [3]: X,O = d['X'],d['O']

• Solutions:

Lab #2, due Tuesday, Sep 21 at beginning of class

• lab2.pdf
• apples.mat
• oranges.mat
• lab2s.m or lab2s.py
• apples2.mat
• oranges2.mat
• lab2m.m

For Python you can use apples-oranges.npz

  In [1]: import numpy as np
  In [2]: d = np.load('apples-oranges.npz')
  In [3]: d.keys()
  Out[3]: ['oranges2', 'apples2', 'apples', 'oranges']

• Solutions:

Lab #3, due Tuesday, September 28 at beginning of class

• lab3.pdf

Matlab code are as separate files below.

• data2d.mat
• faces2.mat
• hebb.m
• eigmovie.m

For Python you can use

• data2d.npz (see previous assignments above for how to read this in)
• faces2.npz
• hebb.py
• eigmovie.py

• Solutions:

Lab #4, due Tuesday, Oct 5 at beginning of class

• lab4
• foldiak scripts (zip)
• sparsenet scripts (zip)
• You will also need the following set of whitened natural movie images: IMAGES.mat
• Solutions:

Lab #5 due Tuesday, Oct 12 at beginning of class

• lab5
• kohonen.m
• showrfs.m

Python code:

• kohonen.py
• showrfs.py
• Solutions:

Lab #6 (Due Tuesday, Oct 26 at beginning of class)

• lab6.pdf
• zip'd Matlab files
• genpat.m
• hopnet.m
• patterns.mat
• corrupt.m

Python code:

• hopnet.py - python version of the above code as one file (with run, genpat, and corrupt methods)
• patterns.npz

   p = np.load('patterns.npz')
   face,hi,X = p['face'], p['hi'], p['X']

   # if you load patterns.mat, use:
   p = scipy.io.loadmat("patterns.mat")
   face,hi,X = [p[k].reshape(10,10).T.reshape(100,1) for k in 'face','hi','X']
   # line above converts Fortran to C ordering

• Solutions:

Lab #7 (Due Tuesday, Nov. 2)

• lab7.pdf
• mog.m
• show_mog.m
• X1.mat
• X1_v6.mat (version 6)
• X2.mat
• X2_v6.mat (version 6)

Lab #8 (Due Thursday, Nov. 11)

• lab8.pdf
• scribble.mat
• scribble_v6.mat (version 6)
• extract_patches.m
• prob.m
• show_patches.m
• boltz.m
• sample.m
• draw.m
• sigmoid.m

Python code:

• boltz.py - python version of the above code.

Lab #9 (Due Tuesday, Nov. 23)

• lab9.pdf
• ica.m
• test_data.mat
• ica2.m
• extract_patches.m
• showbfs.m
• IMAGES.mat