Tuesday, December 05, 2006

For those people who wanted to take part in the interactive review but didn't get a chance..

Folks:
 Those of you who wanted to take part in the interactive review but didn't get a chance because
we ran out of time--please add your comments to the blog--preferaby as a response to this mail.

We will then collect those in making the acquired wisdom page for this year (it seems odd to have
acquired wisdom of only half the clas...)

thanks
Rao

3 comments:

Jeff Walker said...

Things I found of particular interest: search, in particular a* and A-B pruning; planning -- especially partial order planning; all forms of logic, though I find probabilistic logic very fascinating. Bayesian networks are awesome -- you can get a lot for a little.

What kept surprising me over and over again is that the AI concepts taught in this class can be applied to improving my own non-artificial intelligence.

I didn't particularly dislike any of the content, though I found the statistical learning difficult to follow.

Unknown said...

I'm fascinated by the analysis of the human brain as a really good computing device and the application of concepts learned from this analysis to computer science. The section on learning was particularly interesting for this reason.

I also enjoyed learning how Bayes Nets can be used to make difficult problems much more manageable.

Generally, I appreciate discovering the practical applications of AI in the real world and pondering new ones.

Unknown said...

I learned more about the field of AI than I realized was there. I had a glimpse into the field by attending the ALife X conference prior to taking this course, but this course really showed me a lot about what's out there in this field -- and how they relate to many other aspects of CS, Math, statistics, etc.

As was mentioned in class, the projects were very eye-opening into what "exponential algorithms" actually mean; I'm not used to waiting 12+ hours for a result halfway through my analysis. But more than that, the projects gave me an insight into How some problems are solved and I now understand what it means for a game to be "solved" and why games like Go will likely not be solved anytime soon. I understood how Prolog worked prior to this course (I really liked that part of CSE240), but now I understand what goes into thinking about how to Implement a language and the sorts of things that need to be considered.

And while I have always appreciated what we gain from the functional paradigm, and I found myself no longer fighting LISP by the time I was doing Project4, I still think the projects would've been significantly easier in C++ or Java. I don't hate functional programming, I just don't like to code that way. :)

--Andrew.