Prob 1:
-------



Prob 2:
-------

11/25: 
======
There is a bug in the em_gp.m code. 
At line 131 (in function Overall_Log_Likelihood), please change
  ll_i = log_likelihood_gp(V(k,:), t, Y_obs);
to
  ll_i = log_likelihood_gp(V(i,:), t, Y_obs);

i.e. the index "k" should be "i"



Also, the "division by zero" warning happens when the current
cluster has no genes assigned to it. We have changed the code to 
not throw a warning in such a case.
The updated code (which includes the bug fix mentioned above)
is available in hw5/prob2/ sub-directory as code-updated.zip


The input argument "init_class" in em_gp.m is optional, as you 
may have noticed. If not supplied, it is initialized by randomly
assigning each gene to one of k clusters (1..k)


11/27
======
  Some students have reported problems in using plot_results().
This seems to be happening because 't.dat' is being loaded as a
column vector as a row vector. Using t' (i.e, the transpose) instead
of t in the function call should fix this.