VS265: Homework assignments Fall2012: Difference between revisions

From RedwoodCenter
Jump to navigationJump to search
No edit summary
 
(56 intermediate revisions by 2 users not shown)
Line 15: Line 15:
= Assignments =
= Assignments =
==== Lab #1, due Wednesday, September 5th at beginning of class ====
==== Lab #1, due Wednesday, September 5th at beginning of class ====
* [http://redwood.berkeley.edu/vs265/lab1.pdf lab1.pdf]
<!-- [http://redwood.berkeley.edu/w/images/e/ef/Hw1_soln_bilenko.pdf Solution.pdf] -->
==== Lab #2, due Wednesday, September 19th at beginning of class ====
* [http://redwood.berkeley.edu/vs265/lab2.pdf lab2.pdf]
* [http://redwood.berkeley.edu/vs265/data.mat 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 [http://redwood.berkeley.edu/vs265/data.npz data.npz]''
  In [1]: import numpy as np
  In [2]: d = np.load('data.npz')
  In [3]: X,O = d['X'],d['O']
* [http://redwood.berkeley.edu/vs265/apples.mat apples.mat]
* [http://redwood.berkeley.edu/vs265/oranges.mat oranges.mat]
* [http://redwood.berkeley.edu/vs265/lab2s.m lab2s.m] or [http://redwood.berkeley.edu/vs265/lab2s.txt lab2s.py]
<!-- *[http://redwood.berkeley.edu/w/images/2/2c/Hw2_sol.zip Solution_scripts]  [http://redwood.berkeley.edu/w/images/0/05/Solution.pdf Writeup] -->
==== Lab #3, due Wednesday, Sept. 26 at beginning of class ====
* [http://redwood.berkeley.edu/vs265/lab3.pdf lab3.pdf]
* [http://redwood.berkeley.edu/vs265/apples2.mat apples2.mat]
* [http://redwood.berkeley.edu/vs265/oranges2.mat oranges2.mat]
* [http://redwood.berkeley.edu/vs265/lab3.m lab3.m]
''For Python you can use [http://redwood.berkeley.edu/vs265/apples-oranges.npz 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']
<!-- * [http://redwood.berkeley.edu/w/images/9/9d/Hw3_writeup.pdf Solution.pdf] [http://redwood.berkeley.edu/w/images/a/af/Hw3scripts.zip HW3_Scripts] -->
==== Lab #4, due Thursday, October 4 at 9:00 ====
* [http://redwood.berkeley.edu/vs265/lab4.pdf lab4.pdf]
Matlab code are as separate files below.
* [http://redwood.berkeley.edu/vs265/lab4/data2d.mat data2d.mat]
* [http://redwood.berkeley.edu/vs265/lab4/faces2.mat faces2.mat]
* [http://redwood.berkeley.edu/vs265/lab4/hebb.m hebb.m]
* [http://redwood.berkeley.edu/vs265/lab4/eigmovie.m eigmovie.m]
''For Python you can use ''
* [http://redwood.berkeley.edu/vs265/lab4/data2d.npz data2d.npz] (see previous assignments above for how to read this in)
* [http://redwood.berkeley.edu/vs265/lab4/faces2.npz faces2.npz]
* [http://redwood.berkeley.edu/vs265/lab4/hebb.txt hebb.py]
* [http://redwood.berkeley.edu/vs265/lab4/eigmovie.txt eigmovie.py]
<!-- * [http://redwood.berkeley.edu/vs265/sols/hw3-08.pdf Solutions.pdf] This is a solution from a previous version of this class that is really well written. -->
==== Lab #5, due Monday, Oct 15 at beginning of class ====
* [http://redwood.berkeley.edu/vs265/lab5.pdf lab5]
* [http://redwood.berkeley.edu/vs265/foldiak_class_scripts.zip foldiak scripts (zip)]
* [http://redwood.berkeley.edu/vs265/sparsenet_class_scripts.zip sparsenet scripts (zip)]
* You will also need the following set of whitened natural movie images: [https://redwood.berkeley.edu/bruno/sparsenet/IMAGES.mat IMAGES.mat]
<!-- * Solutions [http://redwood.berkeley.edu/w/images/4/41/Hw5_sol_scripts.zip Scripts] [http://redwood.berkeley.edu/w/images/b/b4/Lab5_soln.pdf Writeup] -->
==== Lab #6, due Wednesday, Oct 24 at beginning of class ====
* [http://redwood.berkeley.edu/vs265/lab6.pdf lab6]
* [http://redwood.berkeley.edu/vs265/lab6/kohonen.m kohonen.m]
* [http://redwood.berkeley.edu/vs265/lab6/showrfs.m showrfs.m]
''Python code:''
* [http://redwood.berkeley.edu/vs265/lab6/kohonen.txt kohonen.py]
* [http://redwood.berkeley.edu/vs265/lab6/showrfs.txt showrfs.py]
<!-- [http://redwood.berkeley.edu/w/images/8/8c/Solution6.pdf Solution] -->
==== Lab #7, due Wednesday, Oct 31 at beginning of class ====
* [http://redwood.berkeley.edu/vs265/lab7.pdf lab7.pdf]
* [http://redwood.berkeley.edu/vs265/lab7/patterns.mat patterns.mat]
* [http://redwood.berkeley.edu/vs265/lab7/hopnet.m hopnet.m]
* [http://redwood.berkeley.edu/vs265/lab7/corrupt.m corrupt.m]
* [http://redwood.berkeley.edu/vs265/lab7/genpat.m genpat.m]
''Python code:''
* [http://redwood.berkeley.edu/vs265/lab7/hopnet.txt hopnet.py] - python version of the above code as one file (with run, genpat, and corrupt methods)
* [http://redwood.berkeley.edu/vs265/lab7/patterns.npz 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: The outer product rule to calculate V is given by  X*X' + face*face' + hi*hi'; *
[http://redwood.berkeley.edu/w/images/d/d1/Abbott_ps7.pdf Writeup]
[http://redwood.berkeley.edu/w/images/2/29/Scripts.zip Scripts] -->
==== Lab #8, due Wednesday, Nov. 14 at beginning of class ====
* [http://redwood.berkeley.edu/vs265/lab8.pdf lab8.pdf]
* [http://redwood.berkeley.edu/vs265/mog/mog.m mog.m]
* [http://redwood.berkeley.edu/vs265/mog/show_mog.m show_mog.m]
* [http://redwood.berkeley.edu/vs265/mog/X1.mat X1.mat]
* [http://redwood.berkeley.edu/vs265/mog/X1_v6.mat X1_v6.mat] (version 6)
* [http://redwood.berkeley.edu/vs265/mog/X2.mat X2.mat]
* [http://redwood.berkeley.edu/vs265/mog/X2_v6.mat X2_v6.mat] (version 6)
<!-- * [http://redwood.berkeley.edu/w/images/f/fc/Hw8_solution.pdf Solution] -->
==== Lab #9 (optional), due Monday, Nov. 26 at beginning of class ====
* [http://redwood.berkeley.edu/vs265/lab9.pdf lab9.pdf]
* [http://redwood.berkeley.edu/vs265/boltz/boltz.m boltz.m]
* [http://redwood.berkeley.edu/vs265/boltz/get_batch.m get_batch.m]
* [http://redwood.berkeley.edu/vs265/boltz/sample.m sample.m]
* [http://redwood.berkeley.edu/vs265/boltz/draw.m draw.m]
* [http://redwood.berkeley.edu/vs265/boltz/sigmoid.m sigmoid.m]
* [http://redwood.berkeley.edu/vs265/boltz/scribble.mat scribble.mat]
* [http://redwood.berkeley.edu/vs265/boltz/scribble_v6.mat scribble_v6.mat] (version 6)
* [http://redwood.berkeley.edu/vs265/boltz/extract_patches.m extract_patches.m]
* [http://redwood.berkeley.edu/vs265/boltz/prob.m prob.m]
* [http://redwood.berkeley.edu/vs265/boltz/show_patches.m show_patches.m]
''Python code:''
<!-- * [http://redwood.berkeley.edu/vs265/lab9/boltz.txt boltz.py] - python version of the above code with solution.
* [http://redwood.berkeley.edu/w/images/9/9c/Lab9_soln.pdf Writeup with code] -->
==== Lab #10 (optional), due Monday, Dec. 3 at beginning of class ====
* [http://redwood.berkeley.edu/vs265/lab10.pdf lab10.pdf]
* [http://redwood.berkeley.edu/vs265/ica/ica.m ica.m]
* [http://redwood.berkeley.edu/vs265/ica/test_data.mat test_data.mat]
* [http://redwood.berkeley.edu/vs265/ica/ica2.m ica2.m]
* [http://redwood.berkeley.edu/vs265/ica/extract_patches.m extract_patches.m]
* [http://redwood.berkeley.edu/vs265/ica/showbfs.m showbfs.m]
* [http://redwood.berkeley.edu/vs265/ica/IMAGES.mat IMAGES.mat]
<!-- * [http://redwood.berkeley.edu/w/images/9/99/Lab10_soln.pdf Solution] -->

Latest revision as of 04:14, 19 September 2014

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.

Assignments

Lab #1, due Wednesday, September 5th at beginning of class

Lab #2, due Wednesday, September 19th at beginning of class

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']

Lab #3, due Wednesday, Sept. 26 at beginning of class

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']


Lab #4, due Thursday, October 4 at 9:00

Matlab code are as separate files below.

For Python you can use


Lab #5, due Monday, Oct 15 at beginning of class

Lab #6, due Wednesday, Oct 24 at beginning of class

Python code:

Lab #7, due Wednesday, Oct 31 at beginning of class

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

Lab #8, due Wednesday, Nov. 14 at beginning of class

Lab #9 (optional), due Monday, Nov. 26 at beginning of class

Python code:

Lab #10 (optional), due Monday, Dec. 3 at beginning of class