In this assignment, you will implement and evaluate new Topographica components to get experience in building and testing models. You will also write a short research proposal to get experience with locating and understanding scholarly neuroscientific and computational literature, and selecting research topics. The goal is to end the course in a good position to start constructing novel and feasible visual cortex models using Topographica.
You are encouraged to work in pairs of your choosing. Just submit one copy of the assignment, listing your partner, and the mark will be allocated equally to each. It is ok to work together just on Part 1 if you prefer; in that case, one of the pair should submit Part 1, listing both partners, and the other should submit only Part 2 plus a list of the two partners.
~/cnv
, and launch it:
mkdir ~/cnv cd ~/cnv cp /home/jbednar/public/topographica/examples/tiny.ty . ln -s /home/jbednar/public/topographica/topographica . ./topographica -g tiny.ty
tiny.py
to see how the model is specified, including
how the various parameters are specified. Also study the
SampleHebbian class; this LearningFunction acts as a template for
writing your own LearningFunctions.To create each new rule, make a new copy of the SampleHebbian
code and change both the class name and the super
call.
Then edit the code, removing anything unnecessary and changing
what's needed for the new rule. Note that I have implemented all of
the rules listed above using the type of code already shown in
SampleHebbian, and none of those need some significantly different
approach or very many lines of code. Each rule will require some
new parameters, and you can modify the sample_param and/or value_0
examples to suit.
Now modify your copy of tiny.ty
to use these new
rules, one at a time. This will require editing the values in the
topo.sim.connect2 call to specify your new rule in the learning_fn
parameter, and also may require commenting out the weights_output_fn
if the learning rule is stable. (Be sure to leave weights_output_fn
as DivisiveL1Normalize if the learning rule is not stable, i.e., if
the weight values increase without bound, so that the results will
be well behaved).
Be sure to test that each rule runs and seems reasonable. Then do the following:
Your work must be submitted by 10am Tuesday, 11 April, using the
submit
command on Informatics DICE machines (type
man submit
for more details). Your work should be in the
form of one plain PDF or ASCII file per problem, named as listed
below. ASCII files can be accompanied by PNG images if desired. Late
submissions will not be accepted without good reason, and
will be penalized according to the
standard university policy of 5% penalty per working day or part
of a day.
Example of submit command:
submit msc cnv 2 1_BCM.pdf 1_Oja.pdf 1_Covariance.pdf 2.pdf
Be sure that you provide evidence that you did each part of this assignment. I can only judge what is actually submitted, so you should make sure that the files you submit make it clear that you have done everything, and thought about everything.
Be sure to cite any information that you use that is not from the course material or your own experience. Including such information is encouraged, but it must be properly cited. You can use the CMVC book Bibliography database for citation information for any paper cited in the CMVC text.
Submissions must be in PDF or in plain ASCII text; images can be added separately in .PNG format if necessary. I can be sure to be able to read those formats; others like .doc or .sxw have a certain probability of working, but the probability is far from 1.0. Naming the files as I suggest will make my job a lot easier, because I will be able to see exactly what you are submitting for each problem.
Read and follow my list of writing tips.
Last update: assignment2.html,v 1.4 2006/05/08 04:00:54 jbednar Exp
Informatics Forum, 10 Crichton Street, Edinburgh, EH8 9AB, Scotland, UK
Tel: +44 131 651 5661, Fax: +44 131 651 1426, E-mail: school-office@inf.ed.ac.uk Please contact our webadmin with any comments or corrections. Logging and Cookies Unless explicitly stated otherwise, all material is copyright © The University of Edinburgh |