10. Introduction to Learning, Nearest Neighbors

MIT 6.034 Artificial Intelligence, Fall 2010
Instructor: Patrick Winston

This lecture begins with a high-level view of learning, then covers nearest neighbors using several graphical examples. We then discuss how to learn motor skills such as bouncing a tennis ball, and consider the effects of sleep deprivation.

License: Creative Commons BY-NC-SA

[MM-uhqk]

Thank you MIT. Just found out today that Professor Patrick had passed on the 19th of July, 2019. I am immensely saddened by this incident. I was actually looking forward to meeting you but I guess that is no longer possible. Rest in Peace legend!

[AhmedSALAH-bbun]

RIP Professor Patrick Winston, definitely your work gonna live for ever

[cristiannievesp]

"You have to be very careful about the confusion of correlation with cause. They see the correlation, but they don't understand the cause, so that's why they make a mistake"
This is so simple but so meaningful!

[Andrei-fguv]

this is why MIT is one of the top educational institutions in the world ! Thanks MIT !

[cheng-haochang]

The world is better with you, thanks prof Winston and MIT

[BapiKAR]

This is why I love this prof's lecture.. so much of passion along with simplicity and fun!

[olgxofg]

The last minute of the lecture is gold.

[bxh]

Professor Winston is the best. He is amazing!

[martinmadsen]

I started out going: "This is too slow". Im now on day two, another 10 hour session. The pace of new information is just perfect. You are a great teacher!

[EranM]

46:06 Another thing that is not especially related to the topic is that even when deprived of sleep, the brain works better in the middle of the day rather then the start or end. The huge drops of performance happens when a "subject" is used to sleep/need to sleep. While performance doesn't drop at all (and even goes higher related to the "sleeping time") during the mid-day. Therefore Linear regression can tell you the obvious hypothesis (losing sleep = losing performance) While the Cubic spline can teach you new things you didn't even think of.

[HangtheGreat]

His stories and jokes inspires learning and intuition about the subject. That's good teaching skill right there. I was lucky enough to meet teachers with this skill during secondary my school years but I find really rare in university-level education. Thank you MIT and the late professor for this lecture series

[sassoleo]

These lessons just keep getting better and better

[qzorn]

this mit opencourseware is like eating potato chips you cannot eat just one or view just one lecture. thank you.

[saikumarmv]

Really love the way professor is teaching, his confidence and body language is great ..Thank you very much sir

[flight]

Thanks Patrick Winston for the lively presentations! Thanks MIT!!!

[MathsatBondiBeach]

Taught by Marvin Minsky and a truly class act at so many levels.

[MacProUser]

Boy, he packed a lot into this lecture, but made it so engaging!

[pjakobsen]

Excellent teacher, very organized. He has clearly taught this course many times.

[hengyue]

i can't imagine how much does the knowledge contained in this course worth.

[thechesslobster]

Absolutely blessed to be able to get MIT courses for free.