Just thought I should point this out: that Euphoria video is totally fake (that is, prerendered and not actually generated in real time like they want you to think--it's less impressive than a second year animation student's demo reel). See <a href="http://blog.wolfire.com/2009/11/why-we-are-not-using-euphoria/" rel="nofollow">http://blog.wolfire.com/2009/11/why-we-are-not-using-euphori...</a> for details.
This looks like a summary of the first lecture of the Stanford machine learning course on YouTube:<p><a href="http://www.youtube.com/watch?v=UzxYlbK2c7E" rel="nofollow">http://www.youtube.com/watch?v=UzxYlbK2c7E</a>
I am a bit disappointed, I had hoped the post would compare the strategies used in all these cases...<p>Just saying because I haven't touched machine learning in the last 7 years and think maybe it is time to catch up a bit.
Machine learning and lots of awarded PhDs will likely replace me [a good thing] for the task of neuronal reconstruction:<p><a href="http://t2.ini.uzh.ch/data.html" rel="nofollow">http://t2.ini.uzh.ch/data.html</a><p>If I have to go over several terabytes of images, manually segmenting like that, I'll need to live a thousand lives.