>From the somewhat breathless text up on Wired:
"This is a watershed moment - much more so than Deep Blue versus
Kasparov," says Justin Rattner, Intel's R&D director. "Deep Blue was
just processing power. It didn't think. Stanley thinks. We've moved
away from rule-based thinking in artificial intelligence. The new
paradigm is based on probabilities. It's based on statistical analysis
of patterns. It is a better reflection of how our minds work."
So, does anybody have any insight on these algorithms? Any links/texts
out there to borrow ideas from?
Bruce Butterfield wrote:
>>From the somewhat breathless text up on Wired:
>
> "This is a watershed moment - much more so than Deep Blue versus
> Kasparov," says Justin Rattner, Intel's R&D director. "Deep Blue was
> just processing power. It didn't think. Stanley thinks. We've moved
> away from rule-based thinking in artificial intelligence. The new
> paradigm is based on probabilities. It's based on statistical analysis
> of patterns. It is a better reflection of how our minds work."
>
> So, does anybody have any insight on these algorithms? Any links/texts
> out there to borrow ideas from?
http://www.darpa.mil/grandchallenge05/TechPapers/Stanford.pdf
The last item in the reference is recommended.
Bruce Butterfield wrote:
> Thanks - I've ordered the book.
http://robots.stanford.edu/papers/thrun.probrob.html
Here's a paper to read while the book is on the way.