Unsupervised Learning

Unsupervised learning is the most exciting subfield of machine learning! Finding structure in unstructured data automatically sounds like a dream come true, no need to have a label! In this video, I'll demonstrate 2 types of unsupervised learning techniques; k means clustering and principal component analysis. We'll use these techniques on neural data from a patient suffering from seizures to see if we can locate the part of their brain in need of surgery to save their life. You'll laugh, you'll cry, but most importantly, you'll learn. Enjoy!

Code for this video:

Please Subscribe! And Like. And comment. Thats what keeps me going.

Want more education? Connect with me here:

More learning resources:

Join us at the School of AI:

Join us in the Wizards Slack channel:

Please support me on Patreon:

Signup for my newsletter for exciting updates in the field of AI:

[davidgraham]

When I find myself in times of trouble, a Siraj YouTube video comes to me.

[AntiPolarity]

Please continue to keep it simple. I understood all information in video. With most of previous videos i watched i can't say the same. And thanks for what you are doing!)

[akshaysnimbalkar]

Hi Siraj, my next Data science project is ISL Indian Sign Language Recognition : where i will recognise deaf people gestures and will try to convert it into text and then text to speech.

[MachineLearningwithPhil]

Friggin awesome Siraj. You've inspired me to start my own channel to spread awareness and train the next gen of machine learning experts.

[paulseidel]

Thanks for the clear explanation on eigenvalues and vectors. I never quite understood that until now

[crieyza]

Great video! Quick note: at 8:52 you say "we arrive at a GLOBAL optimum". However, you can only prove that the algorithm will reach a LOCAL minimum.

[nesa]

I am a psychologists and struggling to apply neural net for my master (because there is AI revolution and stuff). I am really surprised that this is topic of your video, since you often talk about new things (for me) with hard core programming and such. I am happy that for once, we psychologists are not to late in the game (topic of your videos). We use some form of PCA for yeaaaars. We used before cool computers (with those card hole things, it is that old) for validation of our personality tests and finding about structure of personality and things like that. Feels good to once be up to date and not technologically inferior. Thanks for great video.

[adhdaddventure]

As i have always stated, THE KING HAS SPOKEN

[apolomachine]

first video i see from your channel.. and you have a new subscriber

[shubhamagarwal]

It is amazing that @Siraj is making videos which are understood by all but Siraj made us fall in love with ML with his old videos only. Sorry man.:)

[georgemavimbela]

Im the Biggest Fan of Siraj
Thank you so much Siraj for the passion in your work

[Aliambarek]

You deserve 1 million likes and Nobel prize

[nullf]

I am so pumped when siraj releases a video

[Ravikumar-lzww]

I was just waiting for one of your video😃and now will start baking this cake😃

[SinanAkkoyun]

*I DONT KNOW WHY BUT MY PC MAKES BUZZY NOISES WHEN SIRAJ MAKES A JOKE D:*

[gaurabbasu]

Thanks, Siraj for the demo.
Learning a lot from your videos.

[ibrahimsani]

Man, you literally helped me with my data science career. You turn downs into ups, complex into simplex or is it simple.
P.s my next data science project would be on identifying Parkinson disease features.

[ZachDoty]

I've been wanting to code an experiment where I use unsupervised learning to cluster memories in a DNC. IMO, this would lead to very human-like memory recall behavior.


Great quote from Yann LeCun, BTW :)

[IvanGoncharovAI]

This is some of the coolest AI videos I've seen in the last while! Great job (and puns), Siraj!

[mohaktrivedi]

Hey Siraj! I love your content!💖
I have one request: Can you please make a video on how AI is being used for wildlife conservation and is it really effective for it?
Cuz, that's my only motive to learn AI! And I wanna know is it even meaningful.
Thank you. Lots of love!😊