Unsupervised Learning: Crash Course AI #6


Thanks to Wix for supporting PBS Digital Studios. Hey, I’m Jabril and welcome to Crash Course
AI! So far in this series, we’ve focused on
artificial intelligence that uses Supervised Learning. These programs need a teacher to use labeled
data to tell them “right” from “wrong.” And we humans have places where supervised
learning happens, like classrooms with teachers, but that’s not the only way we learn. We can also learn lots of things on our own
by finding patterns in the world. We can look at dogs and elephants and know
they’re different animals without anyone telling us. Or we can even figure out the rules of a sport
just by watching people play. This kind of learning without a teacher is
called Unsupervised Learning and, in some cases, computers can do it too. INTRO The key difference between supervised and
unsupervised learning is what we’re trying to predict. In supervised learning, we’re trying to
build a model to predict an answer or label provided by a teacher. In unsupervised learning, instead of a teacher,
the world around us is basically providing training labels. For example, if I freeze this video of a tennis
ball RIGHT NOW, can you draw what could be the next frame? Unsupervised learning is about modeling the
world by guessing like this, and it’s useful because we don’t need labels provided by
a teacher. Babies do a lot of unsupervised learning by
watching and imitating people, and we’d like computers to be able to learn like this as well. This lets us utilize lots of freely available
data in the world or on the internet. In many cases, one of the easiest ways to
understand how AI can use unsupervised learning is by doing it ourselves, so let’s look
at a few photos of flowers with no labels. The most basic way to model the world is to
assume that it’s made up of distinct groups of objects that share properties. So, for example, how many types of flowers
are here? We could say there are two because there are
two colors, purple and yellow. Or we could look at the petal shapes, and
divide them into round petals and tall vertical ones. Or maybe we have some more experience with
flowers and realize that two of these are tulips, one is a sunflower, and one is a daisy,
so there are three categories. Immediately recognizing different properties
like this and creating categories is called unsupervised clustering. We don’t have labels provided by a teacher,
but we do have a key assumption about the world that we’re modeling: certain objects
are more similar to each other than others. We can program computers to perform clustering
too. But to do that, we need to choose a few properties
of flowers we’re interested in looking at, like how we picked color or shape just now. For a more realistic example, let’s say
I bought a packet of iris seeds to plant in my garden. After the flowers bloom though, it looks like
there were several species of irises mixed up in that one packet. Now I’m no expert gardener, but I can use
some AI to help me analyze my garden. To construct a model, we have to answer two
key questions. First, what observations can we measure? All of these flowers are purple, so that’s
probably not the best way to tell them apart. But different irises seem to have different
petal lengths and widths, which we can measure and place on this graph with petal length
on the Y axis and width on the X axis. And second, how do we want to represent the
world? We’re going to stick to a very simple assumption
here: there are clusters in our data. Specifically, we’re going to say there are
some number of groups called K clusters, but we don’t know where they are. To help us, we’re going to use the K-means
clustering algorithm. K-means clustering is a simple algorithm. All it needs is a way to compare observations,
a way to guess how many clusters exist in the data, and a way to calculate averages
for each cluster it predicts. In particular, we want to calculate the mean
by adding up all data points in a cluster and dividing by the total number of points. Remember, unsupervised learning is about modeling
the world, so our algorithm will have two steps: First, our AI will predict. What does the model expect the world to look
like? In other words, which flowers should be clustered
together because they’re the same species? Second, our AI will correct or learn. The model will update its beliefs to agree
with its observation of the world. To start the process, we have to specify how
many clusters the model should look for. I’m guessing there are three clusters in
the data, so that becomes the model’s initial understanding of the world, and we’re looking
for K=3 averages, or three types of irises. But to start, our model doesn’t really know
anything, so the averages are random and so are its predictions. Each datapoint (which is a flower) is given
a label as type1, type2, or type3, based on the algorithm’s beliefs. Next, our model tries to correct itself. The average of each cluster of datapoints
should be in the middle, so the model corrects itself by calculating new averages. We can see those averages here, marked with
Xs, which gives our updated model of the three (or so we guessed) types of irises. The graph is still pretty noisy. For example, it’s a little weird that there
are type2 flowers so close to the average for type3. But we did start with a random model, so
we can’t expect too much accuracy. Logically, we know that irises of the same
species tend to have similar petals, so those datapoints should be clustered together. Since we just did a correction or learning
step, we can repeat the process, starting with a new prediction step. Let’s predict new labels using the Xs that
mark the averages of each label. We’ll give every datapoint the label of
its closest X — type1, type2, or type3 — and then we’ll calculate new averages. That’s better, but still not the cleanest
clusters, so we can repeat the process again: Predict, Learn, Predict, Learn. Eventually, the Xs will stop moving and we
have a model of iris clusters created with unsupervised learning! Now the ultimate question is, did we find
meaningful patterns about the world with our AI? We made an assumption that there were three
types of irises, and we assumed that they have different petal lengths and widths. Was this true? Lucky for us, I have a friend who is a master
gardener. I showed him the real-life flowers closest
to each of the three averages and he said that type1 is Versicolor, type2 is Setosa
and type3 is Virginica. Three different iris species! We learned about the world from observation,
which is what makes this unsupervised learning, even though we relied a tiny bit on a teacher(the master gardener) for confirmation and help. Now that we’ve learned the basics, we can
experiment with harder examples. Let’s say we want to use an unsupervised
learning algorithm to sort a bunch of different photos, not just three iris species. First, what observations can we measure? How much green there is? Whether there’s a nose and fur? To have a computer make these observations,
we need to measure thousands of red, green, and blue pixels in each image. Second, how do we want to represent the world? Before, we were only working with 2 features,
so we could just use averages of the clustered datapoints and get meaningful abstraction
from it. But when dealing with images, we can’t use
the same method, because we won’t get much meaning out of averaging colored pixels for
what we want to accomplish. Somehow, we need the model to create a representation
that tells us if two images are similar. There are meaningful patterns in the data
that are more abstract than individual pixels, and finding them across many images is called
Representation Learning. These patterns help us understand what’s
in the images and how to compare them to each other. Representation learning happens both in supervised
and unsupervised learning models, so we can do it with or without labels to find patterns
in the world. To understand the basic idea of representation
learning, check out this experiment: I’m gonna look at a picture really fast and then
try to draw it. Ready, Set, Go! Woah. That was 5 seconds? My eyes took in the picture and remembered
important features, so I’m building a representation in my mind. But I can’t just show you my thoughts to
get feedback on what parts I misremembered, so I have to produce a reconstruction, or
draw the original image from memory. Alright, so this is what I’ve got. Now let’s compare my drawing to the original image. Let’s see round plate, triangle slice of pizza, some cheese, some crust, tablecloth. Pretty good. For an AI, making a reconstruction would mean
producing all the right pixel values to make a reconstruction. Our K-means clustering algorithm from before,
predicted classes for flowers based on how close the datapoints were to the averages. For images, we will have learned image representations
instead of averages. After that step, just like before, the AI
will have to correct itself. Previously, we updated the K clusters based
on how well our predicted labels fit the data. But for images, we’d have to update the
model’s /internal representations/ based on its reconstructions. There are different ways to use unsupervised
learning in combination with representation learning so that an AI can compare images. Like, for example, there’s a type of neural
network called an autoencoder, which uses the same basic principles of weights and biases
to process inputs, pass data onto hidden neuron layers, and finally to a prediction output
layer. If John-Green-bot was programmed with an autoencoder, the input would be an image, the hidden layers would contain representations, and the output
would be a full reconstruction of the original image (which gets more accurate the more we
train his AI). Theoretically, I could give John-Green-bot
a representation of a pizza and he could reconstruct the original pizza image. What’s so powerful about unsupervised learning
is that the world is our teacher. By looking around, taking in a lot of data,
and predicting what we’ll see and hear next, we learn about how the world works and how
it should be represented. When asked how AI will fulfill its grand ambitions,
2018 Turing Award Winner Professor Yann LeCun,
said: “We all know that unsupervised learning is the ultimate answer.“ So I guess we better keep working on it! Unsupervised learning is a huge area of active
research. The human brain is specially designed for
this kind of learning and has different parts for vision, language, movement, and so on. These structures and what kinds of patterns
our brains look for were developed over billions of years of evolution. But it’s really tricky to build an AI that
does unsupervised learning well because AI systems can’t learn exactly like human often
do, just by watching and imitating. Someone, like us, has to design the models
and tell them how to look for patterns before letting them loose. Next time, we’ll look at applying similar
concepts to AI systems that find patterns in words and language, in what’s called
Natural Language Processing. See you then! Thanks to Wix for supporting PBS Digital Studios. Checkout Wix.com if you’re looking to make
your own website. Wix is a platform that allows you to build
a personalized website for almost any purpose from promoting your business or creating an
online shop to a place for you to test out new ideas. Their technology allows you to create something
unique no matter your skill level with templates and all in one management. If you’d like to check it out you can go
to wix.com/go/crashcourse Or click the link in the description. Crash Course AI is produced in association with PBS Digital Studios. If you want to help keep Crash Course
free for everyone, forever, you can join our community on Patreon. And if you want to learn more about the math
of k-means clustering, check out this video from Crash Course Statistics.

40 Comments

  1. Hanh Dang

    September 20, 2019 at 10:01 pm

    never been so early!

  2. Vern Murphy

    September 20, 2019 at 10:02 pm

    first…nvm

  3. Flash 719

    September 20, 2019 at 10:03 pm

    Early today

  4. Stephanie King

    September 20, 2019 at 10:06 pm

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

  5. Payton Pryor

    September 20, 2019 at 10:08 pm

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

  6. MASTER FAZE SAITAMA

    September 20, 2019 at 10:18 pm

    What happend to your forest ai it was so good

  7. Visual A

    September 20, 2019 at 10:20 pm

    Watching here how AI works seems fun and easy but in reality it's another story

  8. Flaming Basketball Club

    September 20, 2019 at 10:29 pm

    Great series

  9. bowie brewster

    September 20, 2019 at 10:31 pm

    put it at 1.5 speed

  10. Tubmaster 5000

    September 20, 2019 at 10:33 pm

    Hal the computer from 2001 did a lot of unsupervised learning too. The outcome was not good.

  11. Shane Hummus - The Success GPS

    September 20, 2019 at 10:34 pm

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

  12. Geoffrey Winn

    September 20, 2019 at 10:42 pm

    Educational!

  13. HoppingAbout

    September 20, 2019 at 10:51 pm

    Great pizza drawing!

  14. Elaine And John

    September 20, 2019 at 11:37 pm

    Weโ€™re learning about learning. Nicely done, sir!

  15. Don Fields

    September 21, 2019 at 12:27 am

    By supervised learning do you mean programming? Conditioning? Training? Alligning? Or reforming the student? True learning should always begin with learning the simplicity of truth itself…ie: that bieng the only thing one can truly know is that they truly know nothing really.

  16. Mario Roberts

    September 21, 2019 at 12:51 am

    This was a big help fully appreciated ๐Ÿ‘Š๐Ÿฝ

  17. YeezyVII

    September 21, 2019 at 12:54 am

    AI will never exist. not even in a million years. but it's fun to talk about it

  18. NeuroscIQ

    September 21, 2019 at 12:57 am

    Nice talk again. Unsupervised learning is sooo soo cool. I'm working on an unsupervised learning episode of my own! Come check it out

  19. Alexei S

    September 21, 2019 at 1:26 am

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

  20. Nena Anudokem

    September 21, 2019 at 1:36 am

    Best video ever.

  21. Jonathan Williamson

    September 21, 2019 at 1:38 am

    What else are you planting in that garden bro?

  22. Ariel Bintang

    September 21, 2019 at 1:43 am

    Finally seeing him talking with his mouth open…

  23. fidelio

    September 21, 2019 at 2:15 am

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

  24. Goldie O

    September 21, 2019 at 2:16 am

    Homeschoolers call this "unschooling". A method that allows the child to think freely and learn as they want or decide they need to know a subject to go further and learn more. It's not for all kids, but some do quite well with this method.

  25. saviation11

    September 21, 2019 at 3:33 am

    The problem will be human bias in AI. Such as machine hiring….such as in the example that the best candidate for a new CEO position is a white male with a phd from harvard and 20 years experiance……..NOPE lets re program AI to hire a far less qualified woman….. Dont belive it will happen? Google Amazon AI hiring robot. We will F up AI with politics and PC garbage. Watch. It WILL happen

  26. GreenM&M_11

    September 21, 2019 at 3:52 am

    The thumbnail displays such beautiful irises, my lovely Tennessee state flower ๐Ÿ˜

  27. Sandra Kranz Winther

    September 21, 2019 at 4:03 am

    "We want computers to learn like this." Do we? Really?!?!? ๐Ÿ˜ฑ๐Ÿ˜ฑ๐Ÿ˜ฑ๐Ÿ˜‚๐Ÿ˜‚๐Ÿ˜‚

  28. Dull Bananas

    September 21, 2019 at 4:48 am

    Do not leave that robot unsupervised.

  29. directfunebru

    September 21, 2019 at 6:49 am

    Where is this stuff? I'm doing more manual work than ever!

  30. Zangief The Red

    September 21, 2019 at 7:24 am

    The human brain is not "designed", it's evolved.

  31. muffinspuffinsEE

    September 21, 2019 at 9:14 am

    So smooth at talking. I'm juelus.

  32. Pretender

    September 21, 2019 at 9:22 am

    My first brush with machine learning was when I played Black & White. I have it installed on my computer still. Imagine if they made a modern version with even better AI or AI with more processing power.

    Or imagine a creature challenged to complicated tasks and taught by a streaming community on how to solve them.

  33. Alinadan Tigers

    September 21, 2019 at 11:14 am

    For those who want to use AR to classify plants, there is an app called PictureThis. Works surprisingly well

  34. Pesterenan

    September 21, 2019 at 11:18 am

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

  35. Sophos van Alles

    September 21, 2019 at 11:36 am

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

  36. Stephen James

    September 21, 2019 at 11:40 am

    But even the human brain isnโ€™t trained with pure unsupervised or supervised learning. Various feedback mechanisms provide a type of supervision? Such as pain in the case of not touching a hot stove or a parent telling a child not to touch the hot stove. That being said this series does provide a good overview of the current state of the art in AI

  37. Ryan Chapman

    September 21, 2019 at 11:44 am

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

  38. Long Mic

    September 21, 2019 at 2:59 pm

    Is Very good video For Someone To learn AI. Can I repost your video to China Video Sites?

Leave a Reply