http://dl.dropbox.com/u/5137/pdf-link/StanfordAI-UnitOne.pdf
Stanford AI Class Lecture Notes
11–20 of 26 posts
Re: Stanford AI Class Lecture Notes
#12Exported to PDF and re-uploaded for convenience. http://dl.dropbox.com/u/5137/pdf-link/StanfordAI-UnitOne.pdf
Re: Stanford AI Class Lecture Notes
#13Regarding the lecture notes - is there a wiki where we can all contribute to? Earlier today, the google doc was complaining about too many people editing the document.
Re: Stanford AI Class Lecture Notes
#14Google still has a very long way doing an adequate translation between a language such as Chinese and English. I'd be surprised if Google was taking such a pedestrian approach in solving that particular problem. As it stands, languages such as Chinese are intrinsically implicit in nature. In fact, the more adept at the language, the more you can express with less. If you follow the literature back a couple thousand y…
Developers of Google Translate described to me that Finnish is causing problems because the excessive inflection [1] in Finnish language needs a couple orders of magnitude more translated material to make statistical approach to work. At least that time it was not easy to obtain. Interestingly enough, the official EU documents and meeting translations are one of the best sources of 1-to-1 translations as they are translated to all languages in EU.
[1] http://en.wikipedia.org/wiki/Inflection#Uralic_languages_.28...
Re: Stanford AI Class Lecture Notes
#15For example, the interfaces and processors are all very clearly defined and separated in those diagrams. Unfortunately, natural intelligence does not seem to work in the same way. The inputs to a real human do not get processed in the same places, even when they might be coming from the same sensor. Obviously the patellar reflex doesn't make it past the spinal cord, and I've never actually believed that the spectrum of intelligent behaviors can be sorted into "conscious" or "unconscious" categories, by including some sort of wet Boolean or whatever.
We could think of the brain's implementation as the sum of its internal and external interfaces, but how the hell would we model that without involving unreasonable error margins?
Re: Stanford AI Class Lecture Notes
#16Exported to PDF and re-uploaded for convenience. http://dl.dropbox.com/u/5137/pdf-link/StanfordAI-UnitOne.pdf
Do you think you will be doing this more?
I would be incredibly appreciative if you were to set up a mailing list! :D
It's only an idea ;)
Re: Stanford AI Class Lecture Notes
#17Exported to PDF and re-uploaded for convenience. http://dl.dropbox.com/u/5137/pdf-link/StanfordAI-UnitOne.pdf
Most excellent sir! Do you think you will be doing this more? I would be incredibly appreciative if you were to set up a mailing list! :D It's only an idea ;)
Re: Stanford AI Class Lecture Notes
#18Re: Stanford AI Class Lecture Notes
#19Re: Stanford AI Class Lecture Notes
#20Update: Now the videos are saying I need Flash 9 (intro previously worked). Bizarre. I just went to youtube to watch the videos, unfortunately they are not organized well or queued so searching for them is a pain.
This page at least has them all easily accessible: http://www.youtube.com/user/knowitvideos#p/u