Supervised Learning: Crash Course AI #2

Поделиться
HTML-код
  • Опубликовано: 17 ноя 2024

Комментарии • 263

  • @apulcides
    @apulcides 5 лет назад +496

    Dude's so chilled that this crash course is actually in a normal pace.

  • @bracklinnnorah6390
    @bracklinnnorah6390 5 лет назад +203

    That kid getting his test back at 1:47 is the most deeply relatable thing I've seen all day

  • @BKofficer23
    @BKofficer23 5 лет назад +213

    My God that thumbnail is adorable. And the neurons. Whoever designs/animates these images is gifted.

    • @Intoxicatious
      @Intoxicatious 5 лет назад +18

      It's the wonderful people over at Thought Cafe

    • @Danilego
      @Danilego 5 лет назад +5

      I'm pretty sure they're the same neurons from Crash Course Anatomy, which btw is freaking awesome!

  • @mattkuhn6634
    @mattkuhn6634 5 лет назад +749

    As an AI scientist, I appreciated everything in this episode, except for the ridiculous slander against bagels.

    • @mattkuhn6634
      @mattkuhn6634 5 лет назад +44

      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.

    • @wpkepkw3330
      @wpkepkw3330 5 лет назад +20

      Ikr? He is a bagelphobe.

    • @billniko9310
      @billniko9310 5 лет назад

      I didn’t , not everything to learn from this RUclips

    • @billniko9310
      @billniko9310 5 лет назад +2

      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.

  • @kaptongoogle4363
    @kaptongoogle4363 4 года назад +11

    Jabrils explains things using such a simple and understandable language. Love that guy

  • @ianrbuck
    @ianrbuck 5 лет назад +51

    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.

  • @BrainsApplied
    @BrainsApplied 5 лет назад +507

    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 😂😂😂

    • @kekero540
      @kekero540 5 лет назад +98

      Damn Algeria be looking extra thicc.

    • @anouarzekri841
      @anouarzekri841 5 лет назад +3

      @@kekero540 Algeria ???!

    • @kekero540
      @kekero540 5 лет назад +16

      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

    • @adamcollins8907
      @adamcollins8907 5 лет назад +2

      So basically we will be replaced...

    • @kekero540
      @kekero540 5 лет назад +26

      *fertilize the desert*

  • @ASLUHLUHC3
    @ASLUHLUHC3 5 лет назад +125

    2:53 I had no idea neurons were this cute

  • @kaptongoogle4363
    @kaptongoogle4363 4 года назад +24

    I was so surprised to see my favorite youtuber hosting my favorite youtube series

  • @AbrilAFerez
    @AbrilAFerez 5 лет назад +31

    Awesome, I love that this course is now available!

  • @nyanard
    @nyanard 5 лет назад +139

    10% comments: about AI itself,step function
    90% comments: Why he hate bagels?

    • @whitefox8376
      @whitefox8376 5 лет назад +2

      Sadly not even 10%

    • @Ryan-wk3mc
      @Ryan-wk3mc 5 лет назад +11

      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.

    • @peter-peterpumpkineater4982
      @peter-peterpumpkineater4982 5 лет назад +7

      @@Ryan-wk3mc We do now

  • @tando6266
    @tando6266 5 лет назад +60

    The commitment is real, holding up 48 different donuts or bagels so a 'robot' can pretend to determine the outcome

  • @cfromnowhere
    @cfromnowhere 5 лет назад +76

    I wonder who ate all these 100+ donuts and bagels after filming

    • @void2509
      @void2509 5 лет назад +4

      John Green: relaxing
      Also John Green: see 75 begels

    • @maximumjenius8733
      @maximumjenius8733 5 лет назад +2

      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."

    • @billniko9310
      @billniko9310 5 лет назад +1

      11:14 slow down to 0.25x you will see he was not pushing the button

  • @bekacynthia
    @bekacynthia 4 года назад +6

    love his outgoing and chilled personality. But he talked about doughnout so much that I'm craving one right now. Lol!

  • @MTWolfgang
    @MTWolfgang 5 лет назад +4

    Its so good to see a someone explaning something i learned in college, but this animations

  • @kendo4165
    @kendo4165 5 лет назад +7

    Super helpful! Cleared up what bias meant in this context. Thank you!

  • @erickricardoflores8472
    @erickricardoflores8472 4 года назад +2

    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.

  • @scentedcandle7043
    @scentedcandle7043 5 лет назад +11

    I absoutely love this series. Honestly so amazing.

  • @FC_DINDEYA
    @FC_DINDEYA 5 лет назад +60

    This guy is the modern day Tim and moby from brain pop

    • @hinpoppo9185
      @hinpoppo9185 5 лет назад

      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

    • @NoMereRanger73
      @NoMereRanger73 5 лет назад +1

      Awww yeah!!

  • @a_e_hilton
    @a_e_hilton 5 лет назад +71

    Hey, what's all this hate on bagels about? I love bagels!

    • @fairycat23
      @fairycat23 5 лет назад +3

      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.

    • @YourButHed
      @YourButHed 5 лет назад +1

      Hope?

  • @pb-vj1qs
    @pb-vj1qs 5 лет назад +12

    Toasted bagels with cream cheese are great!

    • @cindyzachielrivera373
      @cindyzachielrivera373 5 лет назад +1

      you are making me hungry! I'm going for a bagel now...

    • @eaterdrinker000
      @eaterdrinker000 5 лет назад

      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!

  • @awesaatyanta4309
    @awesaatyanta4309 Год назад

    Best explanation of precision and recall that I've seen!

  • @General_Chaos_Mad_Scientist
    @General_Chaos_Mad_Scientist 2 года назад +1

    I love the pacing of this Crash Course. And I will go buy a donut now

  • @billniko9310
    @billniko9310 5 лет назад +3

    Thank your perfect explanation for AI love ❤️ your RUclips, this is the highest quality series teach AI on RUclips

  • @alfonsoguerrero1180
    @alfonsoguerrero1180 5 лет назад +4

    This episode reminds me of when I had to make KNN models in R.

  • @jakec5618
    @jakec5618 Год назад +1

    This is a great series btw, very helpful in understanding AI. Thanks

  • @DendyJungle
    @DendyJungle 5 лет назад +17

    Sweet bagels are basically donuts. No one tell poor greenbot

  • @rodrickngonyoku5042
    @rodrickngonyoku5042 5 лет назад

    I am So ready for this Course

  • @ShaneHummus
    @ShaneHummus 5 лет назад +2

    Learning is the key!

  • @xxdemonkittyxx8134
    @xxdemonkittyxx8134 4 года назад +2

    I’m kinda jealous how this guy has donuts and bagels, makes me hungry

  • @ulviyye_7232
    @ulviyye_7232 Год назад +4

    9:46 “learns from failure, but not from success” Just like humans

  • @juniormynos9457
    @juniormynos9457 5 лет назад +10

    Damn! He electrocuted the perceptron when it got the answers wrong

  • @arandomperson8336
    @arandomperson8336 5 лет назад

    John Greenbot got a B- on the bagel vs donut test. That's good enough for school!

  • @frapeyou
    @frapeyou 5 лет назад +22

    Woah he talking and not just dubbing over his voice, this is weird

  • @jesondag
    @jesondag 5 лет назад +48

    Who the heck buys 75 bagels and only 25 donuts.

    • @zedek_
      @zedek_ 5 лет назад +7

      A monster.

  • @sihambenlamkaddem2836
    @sihambenlamkaddem2836 Год назад

    Great, helpful video. Your videos never fail to impress me 🙏

  • @kasturirao9582
    @kasturirao9582 4 года назад +1

    who else thinks that his voice is do soothing and he should make a podcast??

  • @yuming8845
    @yuming8845 5 лет назад +1

    Nice to see R.O.B take a break from Smash Bros to join CrashCourse.

  • @purecrystallized
    @purecrystallized 5 лет назад +2

    This series is amazing and so well made!

  • @eunikejovina103
    @eunikejovina103 2 года назад

    love the video, I learned that donut is better than bagels thankyou

  • @dkariningufu
    @dkariningufu 5 лет назад

    The meanest and probably the most elaborate AI algorithm of all is the one putting you in the friend zone

  • @billniko9310
    @billniko9310 5 лет назад +2

    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.

  • @admirald.rifter1819
    @admirald.rifter1819 2 года назад

    This single video helped me understand 10x more of what i understood in my lecture. Thank you

  • @UFBMusic
    @UFBMusic 5 лет назад

    Crossing the Bagel Threshold was the name of my band at fat camp.

  • @barnowlcom
    @barnowlcom 5 лет назад +2

    I love the cassette tape!

  • @billniko9310
    @billniko9310 5 лет назад

    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 .

  • @astrovisionmedia9677
    @astrovisionmedia9677 5 лет назад +3

    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.

  • @Pythos_Sapunov
    @Pythos_Sapunov 5 лет назад +1

    You gotta teach John Greenbot how to keep his bagel from getting away!
    By putting lox on it!

  • @alpercalisirold
    @alpercalisirold 5 лет назад +1

    It’d be really nice if you also touched the XOR problem.

  • @DavidKing-wk1ws
    @DavidKing-wk1ws 5 лет назад +2

    Jabril is the world most advanced artifical intelligence :)

  • @TheAdrian2882
    @TheAdrian2882 5 лет назад +9

    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.

    • @TheTariqibnziyad
      @TheTariqibnziyad 5 лет назад +1

      Go to crash course biology, this is not your place pal.

    • @TheAdrian2882
      @TheAdrian2882 5 лет назад +1

      @@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.

  • @Artfanster
    @Artfanster 5 лет назад

    Nice job getting Omnibot 2000!

  • @FlesHBoX
    @FlesHBoX 5 лет назад

    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!

  • @marwahmaher8574
    @marwahmaher8574 5 лет назад

    I can't wait until this course translated to Arabic to fully understand this exciting course !!
    Please hurry up 🙃 😥

  • @TheOnyomiMaster
    @TheOnyomiMaster 5 лет назад +2

    3:45 Cornell represent!

  • @gibranhenriquedesouza2843
    @gibranhenriquedesouza2843 5 лет назад +2

    I made the Machine Learning course at Coursera, it was nice.

    • @pureconfuzion
      @pureconfuzion 5 лет назад

      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

  • @briancolson3808
    @briancolson3808 5 лет назад +3

    Bagels>donuts... For a super smart guy he's got some underdeveloped taste buds...

  • @susanwilliams2448
    @susanwilliams2448 5 лет назад

    Awesome course. Nice job! I am enjoying it 😍

  • @maximumjenius8733
    @maximumjenius8733 5 лет назад +1

    Everything is delicious, unless of course, they are the bagels. **Insert Bagel Montage**

  • @briannanoren1932
    @briannanoren1932 4 года назад +1

    I love bagels and my nickname at school is bagel

  • @trevorbagels8943
    @trevorbagels8943 4 года назад +1

    Bagels are good too.

  • @blueisnotgreen7258
    @blueisnotgreen7258 5 лет назад +1

    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.

  • @U.K.N
    @U.K.N Год назад

    jabril : blah blah blah
    john green bot : HELLO HUMANOID FRIEND

  • @rmdodsonbills
    @rmdodsonbills 5 лет назад

    I think it's super funny that John Green-bot's programs are saved on cassettes! LOL

  • @JavaAidTutorials
    @JavaAidTutorials 5 лет назад +1

    Nice video..!!

  • @GauravSingh-wj4tn
    @GauravSingh-wj4tn 5 лет назад +1

    green bot's voice is quite similar to "Sheldon cooper" voice from Big Bang theory

  • @Trynil
    @Trynil 5 лет назад

    I like a good dounut but Bagles are my go to day to day.

  • @billniko9310
    @billniko9310 5 лет назад

    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.

  • @stephaniepayne3055
    @stephaniepayne3055 5 лет назад

    Thank you for this information!

  • @shotou
    @shotou 5 лет назад

    I like John Green Bot.

  • @AethernaLuxen
    @AethernaLuxen 4 года назад +1

    Madlad actually counted 100 donuts/bagels

  • @W0lfbaneShikaisc00l
    @W0lfbaneShikaisc00l 5 лет назад

    Thanks John Green Bot!
    Bot: Bagel!

  • @PatrickAllenNL
    @PatrickAllenNL 5 лет назад

    Cool decor

  • @mno2643
    @mno2643 5 лет назад +1

    What's up w jabril being against bagels?? They're so good, especially with cream cheese!

  • @aidenlee2569
    @aidenlee2569 5 лет назад

    yall are really smart

  • @bt7082
    @bt7082 5 лет назад

    Very good!

  • @zhongliangcai602
    @zhongliangcai602 5 лет назад +7

    I never ate a doughnut before, and what is a bagel?

  • @nobufelipe3969
    @nobufelipe3969 5 лет назад +2

    We haven’t master how to have friendly conversations yet. 😆

  • @Great_Olaf5
    @Great_Olaf5 5 лет назад +1

    And here's me, watching all of these, patiently waiting for some mention of bottom up AI. Both videos have been interesting so far, but mimicking human brain function to me is more realistic, if exponentially harder, for getting the results we're ultimately looking for.

    • @o76923
      @o76923 5 лет назад

      Yeah, this has been an incredibly strange way to present it. I'm used to much simpler things like KNN or decision trees being taught early on instead of trying to jump straight into neural networks.

  • @MrIneedalifenow
    @MrIneedalifenow 5 лет назад

    Amazing that ai code can fit on a cassette tape

  • @maximumjenius8733
    @maximumjenius8733 5 лет назад +2

    "I don't wanna bite into a donut and it turns out it's a bagel.", better than biting into a choc chip cookie and finding out they're raisins.

  • @SaudBako
    @SaudBako 5 лет назад

    Not all AI needs to learn. All ML systems need to learn, but not all AI.

    • @o76923
      @o76923 5 лет назад +1

      Not all machine learning systems learn either, counter-intuitively. Some are just algorithms that don't have a learning process.

    • @SaudBako
      @SaudBako 5 лет назад

      James Endicott I thought Machine LEARNING means that the computer is learning. What kind of ML "algorithm" doesn't learn?

    • @SaudBako
      @SaudBako 5 лет назад

      @@o76923 For example, I would consider an intelligent system, which uses hard-coded rules, generally an AI, but not ML unless it learns these rules by itself.

    • @o76923
      @o76923 5 лет назад

      @@SaudBako, fair enough. I've just seen enough people refer to Intelligent Systems with hand coded rules as machine learning that I was willing to lump them together. If you do make a distinction between them, then you are correct.

  • @japan9169
    @japan9169 4 года назад

    I am kinda lost on how the random weighing of Greenbot works
    Also this is a wonderful course

  • @RoulandouII
    @RoulandouII 5 лет назад

    What do you mean by "In our brains, the electric signals between neurons are all the same size"?

  • @zeramino
    @zeramino 5 лет назад

    Very nice.. Thanks!

  • @5Xum
    @5Xum 5 лет назад +3

    This episode gives the impression that supervised learning is neural networks and neural networks only. That makes me sad.

    • @o76923
      @o76923 5 лет назад

      Seriously, I'm worried about them not covering basics first. Is it assumed students came into this already having completed some other crash course series?

  • @frmcf
    @frmcf 5 лет назад

    Why would you use mass and diameter to sort bagels and donuts? Wouldn't other characteristics like sweetness, appearance and providence be more useful? Eg. it looks like it has a frosted topping, it tastes sweet and it came from a donut shop, therefore it's a donut.

    • @dadewoye
      @dadewoye 5 лет назад

      Fraser McFadyen
      He did mention that including more characteristics would increase the processing power needed.
      And the original objective is classifying it before tasting it.

  • @hadywolf5866
    @hadywolf5866 5 лет назад +1

    Dude, I don't know the difference between Bagels and Donuts, and it's not a big deal!

  • @vash6887
    @vash6887 5 лет назад

    I really really want a donut now.

  • @shis10
    @shis10 5 лет назад +1

    9:48 😆😂😂😂From Failure not from success

  • @gosnooky
    @gosnooky 5 лет назад

    I love bagels

  • @lysaali50
    @lysaali50 5 лет назад

    I dislike this man's disgust in bagels
    *BAGELS ARE AWESOME*

  • @wtjreactions
    @wtjreactions 5 лет назад

    This remind me of school.

  • @glitch3141
    @glitch3141 5 лет назад +4

    Why do you hate bagels?

  • @scarletletter4900
    @scarletletter4900 5 лет назад +5

    I did not know that an AI program could fit on an old cassette tape.

    • @Great.Milenko
      @Great.Milenko 5 лет назад +6

      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.

    • @scarletletter4900
      @scarletletter4900 5 лет назад

      @@Great.Milenko Oh, what fun 😃

  • @jamesepace
    @jamesepace 5 лет назад

    What are the blinking lights behind him doing? It looks like it might be the game of life, sorta.

  • @chillsahoy2640
    @chillsahoy2640 5 лет назад

    This type of learning is slightly reminiscent of evolution by natural selection: if your "function for life" is fine, then you survive and all is well. If your "function for life" is not successful, then that particular combination of genes/programs dies out and can be replaced by a slightly different set of genes from another, perhaps more successful, individual. Not a perfect comparison but there is beauty in the system nonetheless.

  • @chunhongbai6526
    @chunhongbai6526 5 лет назад +1

    Cool!

  • @jimmyshrimbe9361
    @jimmyshrimbe9361 5 лет назад

    Awesome!

  • @Ayplus
    @Ayplus Год назад

    I like this