Supervised Learning: Crash Course AI #2
Вставка
- Опубліковано 10 чер 2024
- Today we’re going to teach John Green Bot how to tell the difference between donuts and bagels using supervised learning! Supervised learning is the process of learning WITH training labels, and is the most widely used kind of learning with it comes to AI - helping with stuff like tagging photos on Facebook and filtering spam from your email. We’re going to start small today and show how just a single neuron (or perceptron) is constructed, and explain the differences between precision and recall. Next week, we'll build our first neural network.
Read more about the perceptron and update rule here: jontysinai.github.io/jekyll/u...
Crash Course is produced in association with PBS Digital Studios.
/ pbsdigitalstudios
Crash Course is on Patreon! You can support us directly by signing up at / crashcourse
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, Timothy J Kwist, Brian Thomas Gossett, Haxiang N/A Liu, Jonathan Zbikowski, Siobhan Sabino, Zach Van Stanley, Bob Doye, Jennifer Killen, Nathan Catchings, Brandon Westmoreland, dorsey, Indika Siriwardena, Kenneth F Penttinen, Trevin Beattie, Erika & Alexa Saur, Justin Zingsheim, Jessica Wode, Tom Trval, Jason Saslow, Nathan Taylor, Khaled El Shalakany, SR Foxley, Sam Ferguson, Yasenia Cruz, Eric Koslow, Caleb Weeks, Tim Curwick, David Noe, Shawn Arnold, William McGraw, Andrei Krishkevich, Rachel Bright, Jirat, Ian Dundore
--
Want to find Crash Course elsewhere on the internet?
Facebook - / youtubecrashcourse
Twitter - / thecrashcourse
Tumblr - / thecrashcourse
Support Crash Course on Patreon: / crashcourse
CC Kids: / crashcoursekids
#CrashCourse #ArtificialIntelligence #MachineLearning
Dude's so chilled that this crash course is actually in a normal pace.
That kid getting his test back at 1:47 is the most deeply relatable thing I've seen all day
As an AI scientist, I appreciated everything in this episode, except for the ridiculous slander against bagels.
As a side note, one of the first machine learning programs I ever built was an email filter, which we called a "ham-spam classifier." Makes me almost want to get more emails! Almost.
Ikr? He is a bagelphobe.
I didn’t , not everything to learn from this UA-cam
If we made bagels average small as donuts J green bot will gets more lower precision , diameter and mass has no real causal relations to donuts and bagels. Learning depends on the real causal relations and procedure had been designed to experience. Also procedure design depends on real causal relations.
My God that thumbnail is adorable. And the neurons. Whoever designs/animates these images is gifted.
It's the wonderful people over at Thought Cafe
I'm pretty sure they're the same neurons from Crash Course Anatomy, which btw is freaking awesome!
This reminds me of Google having issues with nudity filters because the color and curves of sand dunes apparently are very similar to naked bodies 😂😂😂
Damn Algeria be looking extra thicc.
@@kekero540 Algeria ???!
Most of Algeria is in the Sahara desert although most of the population lives on the Mediterranean coast. I have a feeling that you already knew that though ;P
معلومة تك
So basically we will be replaced...
*fertilize the desert*
10% comments: about AI itself,step function
90% comments: Why he hate bagels?
Sadly not even 10%
I wonder how many understand that he was just memeing. Digging at John Green's love for bagels as an homage to prior CrashCourse series.
@@Ryan-wk3mc We do now
2:53 I had no idea neurons were this cute
@Karan it's plural
I was so surprised to see my favorite youtuber hosting my favorite youtube series
The commitment is real, holding up 48 different donuts or bagels so a 'robot' can pretend to determine the outcome
+
It's important to note that Supervised Learning and Neural Networks don't always have to go together. You can train a neural network using a different method, and you can use supervised learning on AI models other than neural networks.
I wonder who ate all these 100+ donuts and bagels after filming
John Green: relaxing
Also John Green: see 75 begels
John Greenbot.
Edit: Imagine some guy walking in the their local bakery like: "Hey Jim, I need 100+ assorted bagels... It's for a video."
11:14 slow down to 0.25x you will see he was not pushing the button
Jabrils explains things using such a simple and understandable language. Love that guy
Awesome, I love that this course is now available!
This guy is the modern day Tim and moby from brain pop
Avec un nom comme Boudreau j'aimerais faire l'assomption que ton prof de science en primere était ton expérience avec Brain Pop, et vos etes alle à une école secondaire juste à l'autre bord de la rue
lmao
Awww yeah!!
love his outgoing and chilled personality. But he talked about doughnout so much that I'm craving one right now. Lol!
I absoutely love this series. Honestly so amazing.
Super helpful! Cleared up what bias meant in this context. Thank you!
Its so good to see a someone explaning something i learned in college, but this animations
Hey, what's all this hate on bagels about? I love bagels!
I was wondering that too. I also love bagels. Sure, I don't want to bite into a bagel when I'm expecting a donut, and I don't want to bite into a donut when I'm expecting a bagel, but like... they're both good.
Hope?
Who the heck buys 75 bagels and only 25 donuts.
A monster.
Toasted bagels with cream cheese are great!
you are making me hungry! I'm going for a bagel now...
I disagree with the concept of toasting because I feel that it detracts from the texture and flavor of Noo Yawk bagels (and makes the cream cheese runny and messy). However, you've given me the idea of toasting donuts (particularly the "cake" type), in order to possibly achieve the consistency of home-baked corner pieces of cornbread!
Thank your perfect explanation for AI love ❤️ your UA-cam, this is the highest quality series teach AI on UA-cam
Guys I just want to say thankyou in name of HUMANITY! Your job is so important, and trust me im a communicator myself, I will spread this, and work for the utter common knowledge. Thanks, for real, THANKS.
Best explanation of precision and recall that I've seen!
This is a great series btw, very helpful in understanding AI. Thanks
This series is amazing and so well made!
I am So ready for this Course
Awesome course. Nice job! I am enjoying it 😍
Great, helpful video. Your videos never fail to impress me 🙏
Sweet bagels are basically donuts. No one tell poor greenbot
I love the pacing of this Crash Course. And I will go buy a donut now
This episode reminds me of when I had to make KNN models in R.
Learning is the key!
Thank you for this information!
9:46 “learns from failure, but not from success” Just like humans
I love the cassette tape!
John Greenbot got a B- on the bagel vs donut test. That's good enough for school!
I’m kinda jealous how this guy has donuts and bagels, makes me hungry
lol, I didn't catch the intro theme on the last video so I just thought John Green was tossing some voice clips at your for your channel... Here I am on the second video discovering this is Crash Course.
Good on ya!
love the video, I learned that donut is better than bagels thankyou
Nice video..!!
Very good!
Cool decor
Very nice.. Thanks!
This single video helped me understand 10x more of what i understood in my lecture. Thank you
Damn! He electrocuted the perceptron when it got the answers wrong
Nice job getting Omnibot 2000!
It’d be really nice if you also touched the XOR problem.
The meanest and probably the most elaborate AI algorithm of all is the one putting you in the friend zone
This learning mechanism is one way to design a procedure If Define Design as to select the iteration changing with more successful of adapting goal .
Nice to see R.O.B take a break from Smash Bros to join CrashCourse.
Woah he talking and not just dubbing over his voice, this is weird
So I'm curious, is JohnGreen-Bot an actual AI computer? Or is it just hypothetical? I don't know much about computer science, but I really enjoy watching this course.
Awesome!
yall are really smart
3:45 Cornell represent!
Crossing the Bagel Threshold was the name of my band at fat camp.
who else thinks that his voice is do soothing and he should make a podcast??
I like this
Cool!
A important mistake at 5:31 the electric action potential between neurons are all the same size,yes it is , but also real neuron has the different connection weights to other neurons, so real neuron can do the different size of signal too.
I like John Green Bot.
I made the Machine Learning course at Coursera, it was nice.
I did the initial lessons of the "artificial neural networks" course on Brilliant, which resemble this episode - and it was a light and helpful start. I would like to check the Coursera course too, ty :D
Bagels are good too.
Well during human synapsis the comunication is not only electrical but electrochemical. The levels of that chemical components are what actually produce the answers or the neuron´s electrical shots and that levels are influenced also by many other environmental, genetical or individual inherent conditions. Then is not that easy compare humans and AI or create AI copying human behaviour.
Go to crash course biology, this is not your place pal.
@@TheTariqibnziyad Neuroscience it´s a multidisciplinary area. Then why an AI professional should be talking about biology concepts? It´s all about sharing knowledge, pal.
You gotta teach John Greenbot how to keep his bagel from getting away!
By putting lox on it!
+
Amazing that ai code can fit on a cassette tape
Thanks John Green Bot!
Bot: Bagel!
What's up w jabril being against bagels?? They're so good, especially with cream cheese!
Jabril is the world most advanced artifical intelligence :)
Everything is delicious, unless of course, they are the bagels. **Insert Bagel Montage**
I love bagels and my nickname at school is bagel
green bot's voice is quite similar to "Sheldon cooper" voice from Big Bang theory
9:48 😆😂😂😂From Failure not from success
This remind me of school.
I can't wait until this course translated to Arabic to fully understand this exciting course !!
Please hurry up 🙃 😥
Bagels>donuts... For a super smart guy he's got some underdeveloped taste buds...
jabril : blah blah blah
john green bot : HELLO HUMANOID FRIEND
I like a good dounut but Bagles are my go to day to day.
We haven’t master how to have friendly conversations yet. 😆
I almost understand that supervise learning but I can't understand how did you put that ai program only by the cassette tape
I really really want a donut now.
1:29 I did not understand this youtube example, could somebody help me understand wether by sharing a link or explaining?
I love bagels
What are the blinking lights behind him doing? It looks like it might be the game of life, sorta.
I think it's super funny that John Green-bot's programs are saved on cassettes! LOL
I never ate a doughnut before, and what is a bagel?
What do you mean by "In our brains, the electric signals between neurons are all the same size"?
Crash Course what software do you use to create the title for thumbnailing?
Madlad actually counted 100 donuts/bagels
I am kinda lost on how the random weighing of Greenbot works
Also this is a wonderful course
I know this is simplistic for the purpose of explaination but they really missed an opportunity to add a simple classification based on the ratio of mass to size. If it’s large it’s a bagel unless it’s light. Truly the fact that we’re picking light for donuts and heavy for bagels is good but Considering that all the data is there it makes more sense to do it as a ratio.
i like bagels and donuts
At 2:53 this description to neuron’s working mechanism is simple as too simple as easy to mistake students to understand. Reality the working mechanism of neuron has been designed more much complex than you think (because of natural selection).
3:10 neuron talking to each other by passing neurotransmitter (and the electrical signal is not the only way the neuron talking to another neuron)
And the neuron isn’t using electric action potential directly to another neuron (this animation will makes you think wrong easy) the electric signal will makes the neurotransmitter transmit to another neuron and it will not save the energy if the previous one sends the neurotransmitter it doesn’t recognize.
I did not know that an AI program could fit on an old cassette tape.
of course it can , a standard audio cassette could hold around 130mb of audio data (like that of a dial up modem) thats plenty for simple AI.
but cassette technology has come a long way. standard sized data cassettes used for backup and storage can hold MANY gigabytes of data, and some newer ones can hold more than a hundred terrabytes. ...the problem comes from random read cycles... it takes hours to load all of the data from the cassette.
@@dixie_rekd9601 Oh, what fun 😃
What you got against bagels?
Aye early gang 💪🏾
Well now I want a donut
I love it, but I need a faster tempo, you know?
Playback speed is in the options. I'll watch most videos at 2x speed after getting tired of slow tempos.