Yeah, I've head similar problems with some of the machine learning classes as 
coursera. I've really like udacity's program though, not sure if you've checked 
it out? They've got two AI courses, one the classic Intro to AI that covers a 
little bit of everything:

https://www.udacity.com/course/cs271


I used the first version to help me with a general AI course I took last year. 
They also have a more advanced AI for Robotics class that goes into robot 
planning using probabilistic methods:

https://www.udacity.com/course/cs373


I'm taking this one now. Overall I like their set up better than coursera's 
(although it's still really good). They don't have as much classes, but they 
incorporate videos and short programmng quizes in a way that makes it easier to 
understand and apply. Their program is also self-paced so you don't have to 
worry about Coursera's deadlines, just learning the material and getting the 
work done. For both though, I've found I have to have a textbook for review and 
to get the full background and proofs behind the concepts. It just doesn't work 
for me otherwise.

-Chris



________________________________
 From: Jim Bromer <[email protected]>
To: AGI <[email protected]> 
Sent: Friday, January 25, 2013 7:29 PM
Subject: [agi] I may be destined to be a hopeless dropout from online 
introductory courses in AI
 

I am taking two Introduction to AI online courses and I am making quite a few 
mistakes.  Some of the mistakes are just plain mistakes. But some are due to 
annoying cutsieness.  Here is an example:
 
True or False
State transition systems can represent actions that occur in parallel.
 
Well of course they can, but since this is an introductory course the answer 
has to be False.
Ok, got that one right.
 
A state transition graph may have multiple outgoing/incoming directed edges 
that are labelled with the same action.
 
Well I had a feeling that was a trick question given the answer to the first 
question, and the answer is...True. True?  My best guess is that the term label 
was not being applied to *some particular* labelled actions but to the choice 
of actions at a particular state, whereas each state is the resultant of the 
action so they are thought of as particulars (like values)?  Maybe there is 
some other reasoning behind this but if there is I can't figure it out.
 
This was from an introductory course in AI planning. AI Planning!  I find this 
stuff intensely annoying.  We cannot use a state transition diagram to diagram 
parallel actions?  (That would be impossible for anyone to even consider. Your 
mind can't handle it.)  But it can be used to represent multiple 
outgoing/incoming directed edges labelled with the same action?  Is the teacher 
kidding? Maybe you guys who have already been through this see some error that 
I don't see, but I just don't see why the teacher cannot just come out and 
explain the conventions that are applied to terminology (like "state transition 
diagram") and save the quizzes for the good stuff. Why challenge the students 
with the professor's mastery of ambiguity?
 
I make a lot of really dense mistakes in these courses.  I don't want to waste 
my time trying to outwit the teacher's challenges about computational 
phlogiston.
 
Jim Bromer
 
 
AGI | Archives  | Modify Your Subscription  


-------------------------------------------
AGI
Archives: https://www.listbox.com/member/archive/303/=now
RSS Feed: https://www.listbox.com/member/archive/rss/303/21088071-f452e424
Modify Your Subscription: 
https://www.listbox.com/member/?member_id=21088071&id_secret=21088071-58d57657
Powered by Listbox: http://www.listbox.com

Reply via email to