Unsupervised Learning: Crash Course AI #6

Today, we’re moving on from artificial intelligence that needs training labels, called Supervised Learning, to Unsupervised Learning which is learning by finding patterns in the world. We’ll focus on the performing unsupervised clustering, specifically K-means clustering, and show you how we can extract meaningful patterns from data even when you don't know where those patterns are.

Crash Course AI is produced in association with PBS Digital Studios

Thanks to the following patrons for their generous monthly contributions that help keep Crash Course free for everyone forever:

Eric Prestemon, Sam Buck, Mark Brouwer, Indika Siriwardena, Avi Yashchin, Timothy J Kwist, Brian Thomas Gossett, Haixiang N/A Liu, Jonathan Zbikowski, Siobhan Sabino, Zach Van Stanley, Jennifer Killen, Nathan Catchings, Brandon Westmoreland, dorsey, Kenneth F Penttinen, Trevin Beattie, Erika & Alexa Saur, Justin Zingsheim, Jessica Wode, Tom Trval, Jason Saslow, Nathan Taylor, Khaled El Shalakany, SR Foxley, Yasenia Cruz, Eric Koslow, Caleb Weeks, Tim Curwick, David Noe, Shawn Arnold, Andrei Krishkevich, Rachel Bright, Jirat, Ian Dundore
--

Want to find Crash Course elsewhere on the internet?

#CrashCourse #ArtificialIntelligence #MachineLearning

[paytonpryor]

I love this dude. He's so cute, intelligent, and super chill.

[pesterenan]

WAIT? JABRILS ON CRSSH COURSE AND NOONE TOLD ME? I gotta start from the beginning, BRB.

[mintcarouselchannelabandon]

aaa as a linguistics nerd im excited for this next topic (also as an aside- there should really be crash course in linguistics)

[elaineandjohn]

We’re learning about learning. Nicely done, sir!

[Ryan-wkmc]

So far, easily one of my favorite crash course series. Keep it up! It's great.

[EwemizDreamsRawks]

How exactly does representation learning/reconstructing one picture allow an AI to see if two images are similar? The example provided only talked about reconstructing one image, and not comparing two. Also, why would a neural network need to reconstruct an image when the original image pixels' data is already there?


(I'm really new to AI, and I've enjoyed this series so far! I'm just a little confused about this one. Many thanks to anyone who can help!)

[ShaneHummus]

Awesome content brother! I have been your subscriber for quite some time now. You have been a great help.

[SingularityAGI]

I wish all the crash course videos are this clear in speech deliverence.

[stephanieking]

I screamed when I saw Jabrils! Im so happy for him!!

[GreenMM_]

The thumbnail displays such beautiful irises, my lovely Tennessee state flower 😍

[sophosvanalles]

Whoah! How are we 6 episodes in and this is the first time I've seen this series??

[AL-tfbj]

Love his vibe. Almost looks like he is singing in meaningful information if you mute it

[chemistryfiles]

AI is amazing. Im thinking of all the ways it could improve chemistry.

[muffinspuffinsEE]

So smooth at talking. I'm juelus.

[marioroberts]

This was a big help fully appreciated 👊🏽

[patrickibrahimi]

u just saved my life with this video <3

[avnertishby]

This is a fantastic series!
Well done!

[codeiguess]

I had literally never seen this man's mouth move.

[esthermofet]

Hugely informative... but I think we’d do well by having a primer of sorts. For example, the tools to use to explore machine learning, some rudimentary or introductory tasks to get going. Theory is important, yes, but it only goes so far. Learners need to have an example of _something_ to mimic.

[spaminbox]

the week is so long waiting for a new one of these to release.