Mathematics of Machine Learning

Поділитися
Вставка
  • Опубліковано 9 лис 2024

КОМЕНТАРІ • 441

  • @kalebbruwer
    @kalebbruwer 6 років тому +462

    All those people who say, "Math is useless and you don't use it in the real world" are about to be replaced by machines running on all the types of math people tend to hate.

    • @seyiojewale7907
      @seyiojewale7907 5 років тому +1

      Tell 'em

    • @Douglas12ds54
      @Douglas12ds54 5 років тому +1

      @Lukas 96 This is not a threat, this is an *warning*!

    • @morpheus7422
      @morpheus7422 5 років тому +5

      I'm beginning to understand why I learnt these maths in high school.

    • @Douglas12ds54
      @Douglas12ds54 5 років тому +3

      @@morpheus7422 And I started to regret because I skipped those classes in the Highschool

    • @watson8087
      @watson8087 5 років тому

      😂

  • @hammadshaikhha
    @hammadshaikhha 6 років тому +85

    Yo Siraj, this was a awesome and simple video. I think you have figured out the best combination of pacing, math, animations, and memes now. I would appreciate if you made more videos like these on topics like decision trees, SVM, back propagation, etc. I know you have covered these topics before but I feel the quality of videos now is a lot better for learning. Like there is a huge difference between this video which you can really learn from and your "backpropogation in 5 minutes".
    Anyways I will submit for the challenge for this week, looking forward to other submissions as well.

  • @tanbirsohail
    @tanbirsohail 6 років тому

    This is my favourite channel to get introduced to everything in machine learning.

  • @camilocarrillo2132
    @camilocarrillo2132 6 років тому

    this guy is not crazy at all, after 1 day of watching videos(far more fun and efficient than articles) I understand almost everything, say 80% being ML calculus and back propagation the hardest. That being said I know nothing about calc so it's a bit harder for me to grasp the concept, anyone familiar should have no problems. Next challenge is to fully understand the calcs behind and then python the stuff. Great channel!

  • @umakanetkar1605
    @umakanetkar1605 Рік тому

    Brilliant video! Have been studying Machine Learning for a while but never knew what foundations it has been built upon. Thank you!

    • @davidmurphy563
      @davidmurphy563 Рік тому

      This man is a charlatan and has not the first idea of the maths behind machine learning. He famously plagiarised a paper on AI and, do avoid getting caught like a naughty child he changed "logic gate" to "logic door" and complex Hilbert space to complicated Hilbert space. He didn't know what the basic component of a computer is or that a complex number is a number with a rational and irrational component.
      There are some great channels covering the maths of machine learning (eg Khan Academy) - this is not one of them.. Your grandmother knows more about math than this fraud.

  • @michaelfalkenberg1930
    @michaelfalkenberg1930 6 років тому +1

    Am currently learning Python to assist in corpus analysis within linguistics, everytime i get bored or demotivated I watch one of your videos to see what it is that programming can do and I get back to work. Thanx.

  • @tylerangert9121
    @tylerangert9121 6 років тому +64

    your video editing is getting much better :) i also can really tell you are working on your pacing and presentation tone. very good content.

  • @kvzound
    @kvzound 6 років тому +258

    Sentdex ❤

    • @ХристоАврамов-ф3й
      @ХристоАврамов-ф3й 6 років тому +1

      Could you tell me the what's the name of this vid that sentdex has uploaded?

    • @CodeEmporium
      @CodeEmporium 6 років тому +4

      I think that video is from Him explaining HaarCascades in OpenCV

    • @anshchugh991
      @anshchugh991 6 років тому +2

      its tensorflow obect detection video

  • @vigneshpadmanabhan
    @vigneshpadmanabhan 5 років тому +2

    I haven’t seen anyone explaining the use of math in such a wonderful way for machine learning until now. If you could make the Andrew ng ML and DL series with python .. I will be the first to join and I am pretty sure everyone here will join . I really need a course which covers everything overall man .. right from math to programming to algorithms ... you never get the right structure anywhere and investing time that way is tough man given the time I have daily .. working and studying after 9pm is tough.. I wanna invest 2 hours of my day for this, if there is a well structured course available. I really wish you do this whole thing.

  • @klopkerna3562
    @klopkerna3562 5 років тому +36

    You didn't talk about complicated Hilbert space. I'm so disappointed. 😥

    • @vishalshete5820
      @vishalshete5820 4 роки тому

      Guys forgive him and stop doing so muth hell of overacting

  • @ozland7172
    @ozland7172 5 років тому +1

    I am literally enlightened on this subject.. i studied maths but never made sense so much! thank you!!!

  • @nickjoseph6047
    @nickjoseph6047 5 років тому +2

    "Like a nice... bowl." Killed it. Great job, Siraj!

  • @SabbirAhmedSibli
    @SabbirAhmedSibli 6 років тому +9

    Summery of the ML Stanford course by Mr. Ng :) Nice explanation btw..

  • @darrellwoodwood553
    @darrellwoodwood553 5 років тому +13

    Thank you Siraj for the clear, accurate, concise and enlightening overview of machine learning. It answers my most fundamental question that is always on my mind, viz., Why am I doing what I am doing? Thanks again!

  • @tejasvagarwal5151
    @tejasvagarwal5151 6 років тому +7

    Please include this video in your playlist of maths of intelligence. I love that playlist and watch it once in a month.
    Cheers

  • @hrishiwagh9916
    @hrishiwagh9916 6 років тому

    Man, this is the video which made me really understand where i am standing (in terms of learning) and what needs to be learnt more. Came as a motivation for me. :) :)

  • @mohamedbilal5634
    @mohamedbilal5634 6 років тому +131

    Machine Learning is Math

    • @EqualConnectCoach
      @EqualConnectCoach 6 років тому +5

      Not exactly all

    • @stardaggerrihannsu2363
      @stardaggerrihannsu2363 6 років тому +9

      Math is Fun, and Calculus is the "Great Divide" between those who can do Science, and those who are just screwing around.
      When I hire people, the first question is "Do you know Calculus?", then a problem, even for social science positions.

    • @ko-Daegu
      @ko-Daegu 6 років тому +4

      EqualConnect Coach
      Show me something that doesn’t use math .....
      One thing only ....

    • @ko-Daegu
      @ko-Daegu 6 років тому +1

      StarDagger Rihannsu
      Oooh really nice info ...
      For someone who wanna start working in this field

    • @JobFormAutomator
      @JobFormAutomator 4 роки тому +1

      Deep

  • @VikasKumar-ef1in
    @VikasKumar-ef1in 6 років тому +2

    Spot On, Siraj, I have seen many blogs/videos but this one, was exactly, what I was looking for. Request you to please make 2 or 3 videos with different examples with more explanations. And one suggestion/Initiative for you, can you create one page/website/your channel, where like minded people and your fans (We) can post queries and get solutions by you or your fans ? Its just a thought. Thanks.

  • @jiyaadnaeem4802
    @jiyaadnaeem4802 6 років тому

    Absolutely beautiful explanation of where different disciplines come in to solve a real Machine Learning problem - especially since I was looking for an apartment around NYC :) . Thank you so much for this!

  • @JonathanDoAl
    @JonathanDoAl 6 років тому

    Wow!! I have been studying machine learning for quite a while, and you my friend have just summarized the main aspcts of it, in a simple and precise explanation. Of course, talking only about supervised learning :)

  • @gakukid991
    @gakukid991 6 років тому

    I like how you always put resources in the description. Thanks

  • @mariamonica9128
    @mariamonica9128 6 років тому +12

    Siraj, I love your videos, I watch them with subtitles because I am learning English still😀, I intend to enter this area in the future. Congratulations 👏👏😊

    • @arunachaleshwaran
      @arunachaleshwaran 6 років тому

      That's simple ... Just need high dedication to learn

    • @jaedeepmakwana4551
      @jaedeepmakwana4551 6 років тому

      Monica Rocha I m English teacher.. Do you want to learn English perfect?

    • @MrMatheus195
      @MrMatheus195 5 років тому

      Monica Rocha Ora, ora, uma br aqui...E aí, como que está os estudos? Atualmente também tô querendo entrar nessa área de Machine Learning, se puder dar umas dicas ficaria agradecido kk

    • @laca852
      @laca852 5 років тому

      @@jaedeepmakwana4551 Engineering *quastions* Mr English teacher? ua-cam.com/channels/RINI21jDSboANYuERxqZXQ.html

  • @meetthereqs
    @meetthereqs 6 років тому

    Dude I'm struggling with Induction proofs because it's been awhile since I last mathed but thank you for changing my perspective yet again.

  • @spunpum
    @spunpum 6 років тому

    Wow, it's the first time I see your videos. You are doing an awesome job here. The world needs more people like you. Thank you very much for doing this.

  • @SanulRaskar
    @SanulRaskar 6 років тому

    Thanks for the video 👍. I really enjoying your videos regarding ML. I have started gaining more interest in ML by watching your simple videos

  • @andrewzelin7515
    @andrewzelin7515 4 роки тому

    Hi - a very informative and succint video of how these 4 areas of maths come together to lead to Machine Learning - thanks, Siraj! I am now able to use back-proagation to find a solution to a predicive / regession model! Happy to share my code!

    • @RoyalBengalCub
      @RoyalBengalCub 4 роки тому

      Hello!
      We are researchers in human-computer interaction (HCI) looking for people who have taken an initiative to recently learn Machine Learning on their own, for career, course or curiosity. Tell us here (www.surveymonkey.ca/r/SelfLearning_ML) about your experiences and any difficulties you faced while self-teaching ML and how you overcame them, and have a chance to win $50 giftcard.
      You can help this project by taking out 5-10 minutes to participate in our study. People from any major/background may participate.
      For more details, see here: www.surveymonkey.ca/r/SelfLearning_ML
      Please share this request with your colleagues or friends who fit this description. The survey will be open until July 20, 2020.

  • @kazimrahman7499
    @kazimrahman7499 6 років тому

    WoW....!!....Excellent Demonstration....looking forward for some more lessons from you on [ Statistics,Calculus, Linear Algebra, and probability] with the basis of Machine Learning and Data Engineering.....thanks...!!

  • @BeastModeDR614
    @BeastModeDR614 6 років тому

    The best channel on youtube

  • @roomiat
    @roomiat 5 років тому +1

    Bro you are epic. I was watching your video for machine learning and it gave me an idea about beam steered radar calibration. thanks

  • @avalon2199
    @avalon2199 4 роки тому +1

    *Clear and concise. Great content and explanation*

  • @adityakaranth8619
    @adityakaranth8619 5 років тому +1

    This just blown my brain away.. Thanks a lot Siraj

  • @Garentei
    @Garentei 5 років тому

    Thank you. Your channel is one of the few ones ML that I actually understand.

  • @harshad2227
    @harshad2227 6 років тому

    Love Siraj & Sendex.
    It would be great if you can make a video on ,where and how ML and AI can be implemented in physical machines like robots, industries, automation etc.

  • @periyava3660
    @periyava3660 5 років тому

    No one could do this job better than you, Great job!

  • @windgentle1557
    @windgentle1557 5 років тому

    At 7:40, it should be “multivariable” regression rather than “multivariate” regression because the latter refers to multiple response variables.

  • @AbhayPandey-jo6nh
    @AbhayPandey-jo6nh 6 років тому

    Thank you so much .... Siraj .... This is the best video I have ever seen. It clearly helps in understanding basic termnology for machine learning......
    Thank you so much and keep making such videos😊😊😊

  • @besong-anongernest
    @besong-anongernest 5 років тому

    I feel like Siraj gets me. Maths is very new essential

  • @Samson-cr3ly
    @Samson-cr3ly 6 років тому

    Thanks for your work, Siraj. Your videos and personality make learning from you a fun experience.

  • @keenanburkepitts
    @keenanburkepitts 6 років тому

    This is a really succinct and digestible breakdown. Props!

  • @fabdenur
    @fabdenur 6 років тому

    Siraj, in the case of linear regression that minimizes the sum of squared errors, one doesn't need to (and in general shouldn't, due to computational cost) use an iterative algorithm. Unlike most machine learning models, this one admits a straightforward analytical solution -- that is, a closed-form formula.
    To find the formula for the global minimum (shown in the link below) just take the derivative with respect to the explanatory variable x (which might be a vector of variables), set it to zero, then solve it via basic linear algebra. It's easy to show (by showing positive definiteness of its Hessian) that the error function in this case is convex, so the solution to the above procedure gives a global minimum.
    For more details, see for instance
    en.wikipedia.org/wiki/Least_squares#Solving_the_least_squares_problem
    best

  • @vishalmishra3046
    @vishalmishra3046 3 роки тому

    How about the mathematics of all the new stuff - deep-learning/neural-nets, CNNs, RNN/LSTM, transformers/attention-networks, GPT-3, Alpha-Fold2 etc. ?

  • @hitman779
    @hitman779 6 років тому

    I wach your movies for like 1,5 year. Finaly I understand everything!

  • @rodolfoblasser3329
    @rodolfoblasser3329 5 років тому

    Hi friends. On this specific subject (multivariable regression) I recommend everyone to check on Professor Wooldridge's CEO salary case where you can perform a regression on many variables in order to determine how each one explains the dependent variable (CEO's salaries). Go econometrics!

  • @JosephRivera517
    @JosephRivera517 4 роки тому

    Thanks for the idea, especially for those who are starting out.

  • @chichan2818
    @chichan2818 5 років тому +6

    Sounds like when someone talks about machine learning knowing only high school math

  • @BEPEC
    @BEPEC 6 років тому

    Math is the key topic in Machine Learning

  • @hendriknieuwenhuizen4397
    @hendriknieuwenhuizen4397 2 роки тому

    Wow thanks for thr good presentation. Who loves a challenge?

  • @ManajitPal95
    @ManajitPal95 6 років тому +48

    ah! andrew ng's example!

    • @aaroldaaroldson708
      @aaroldaaroldson708 5 років тому +3

      Exactly! :)

    • @DeepTuts
      @DeepTuts 4 роки тому +7

      My first time trying his video because I heard he was a fraud. And seeing this proved it

    • @michelberden3717
      @michelberden3717 3 роки тому +1

      @@DeepTuts what did he do?

  • @maheswarisrinivasan8391
    @maheswarisrinivasan8391 5 років тому

    You are excellent! Superb! Graph! Animations ! Easy to understand! I'm wordless!

  • @babayaga168
    @babayaga168 6 років тому

    This was better than many, but still its not good for beginners. I means lot of things are not told detail. I might sound totally stupid with below questions, but I am a beginner
    Q1. How do you get this pink line at 2:55 ?
    Q2. in Y=mx+b, how can X be independent ?
    Q3. In this video where specifically you told about the prediction that was made by algorithm we develop , and how we compare it with the correct data ?

  • @chromashift
    @chromashift 6 років тому +1

    🔥🔥🔥. Awesomely motivational, & enlightening. The “wizards of oz” will be so sad that you’re making the compex accessible.
    🤘🏼🤓🤟🏼

  • @smartsniper268
    @smartsniper268 6 років тому

    The main advice is Explore MATH..👌👌👌

  • @samuelson8522
    @samuelson8522 6 років тому

    This is very insightful. Good start to machine learning.

  • @rohanhazra7622
    @rohanhazra7622 6 років тому

    ML videos are awesome, but please upload more coding videos on Distributed Systems

  • @krishnakumar-gc6hb
    @krishnakumar-gc6hb 6 років тому

    Please do make videos on this order exploding different regression methods... Very excellent video

  • @musficamurshidopshori2512
    @musficamurshidopshori2512 6 років тому

    Please make more videos on Machine learning and artificial intelligence. IF possible, then also on thesis related to ML.

  • @rajshah9031
    @rajshah9031 6 років тому

    You are awesome bro. You explain the topic in the easiest way

  • @kitgary
    @kitgary 6 років тому

    Maths is the biggest barrier for most people (include myself) to learn machine learning! Many people just give up because they can't handle maths and programming at the same time.

    • @KigbuPatrickkpk
      @KigbuPatrickkpk 6 років тому

      Using sk-learn, you can focus on the programming

  • @urban9756
    @urban9756 6 років тому

    make video on what are requirements to predict stock prices with machine learning

  • @TheKarstrasse
    @TheKarstrasse 5 років тому

    Awesome video. Crisp and clear.

  • @bobsmithy3103
    @bobsmithy3103 6 років тому +1

    This reminds me a lot of Giant_Neural_Network's neural network beginner series.

  • @5621346
    @5621346 6 років тому

    nice set of graph!

  • @codewizard8892
    @codewizard8892 6 років тому

    Sir your content is really great, Presentation is really excellent. But please give a pause to digest your words .

  • @rafaelnunes000
    @rafaelnunes000 6 років тому

    Yessss Siraj!! Yess! SLOWER vids!!! Excellent!! :D

  • @michaelmebratu2921
    @michaelmebratu2921 5 років тому +4

    Siraj you're the best

  • @mrhahapotter
    @mrhahapotter 4 роки тому +1

    Wow
    You are one of the best ML of youtube . It is so hard to find information on the russian .Good luck for your business .

  • @treybrown599
    @treybrown599 6 років тому

    Excellent Video, Siraj! Thank you!! :D

  • @jakeliujakeliu
    @jakeliujakeliu 6 років тому

    Thank you for create those video, you make learning AI so much fun and easier!

  • @vishalshete5820
    @vishalshete5820 4 роки тому

    You are awesome siraj

  • @mind.journey
    @mind.journey 6 років тому +2

    Subscribed! My problem is that each of these fields is really vast, in fact you could spend years and still not be done learning statistics or linear algebra.
    Could someone point out some good resources to learn each one of these disciplines?

    • @apamwamba
      @apamwamba 2 роки тому

      This stuff i staught in a four year degree program at most universities. But i know some Machine learning experts with a non mathematical background. The question really is how much of Stats, Probability , linear algebra and Calculus do you need to do machine learning at a practical level? Mastering these subjects is a lifelong effort...I did this stuff myself [Bsc Mathematics] and much more like Real Analysis BUT much of it is forgotten...I now eran a living from SQL , Databases and Excel.... But this is a very good video as it summarises the nitty griity with a practical example. Exellent work

  • @valoredramack9117
    @valoredramack9117 5 років тому

    So this Fall Quarter 2019, I'm getting ready to finish Calculus I in college which taught me how to work with Toolkit Functions, Derivatives, Limits, Domains, Ranges, Power Rule, Quotient Rule, Product Rule, Chain Rule, L'Hopital's Rule, and Logarithmic Properties. My question is....do I need to take Calculus II and III to be able to understand the algorithms used in Machine-Learning? Because I would much rather be taking more programming courses. I'm already familiar with some ML functions like Sigmoid, ReLu, and TanH; but I have not yet built my first artificial neural network. Personally, I enjoy Statistics more than Calculus, so I'm hoping that I don't need to take more Calc courses to be successful in this field. I've already taken Stats 1 which taught Standard Deviation, Variance, Distribution, and a few other concepts, but it didn't cover Linear Regression and my Calculus course hasn't covered Gradient Descent. If there are only a few more essential topics for the math used in ML, then I can learn on my own if I know what to study.

    • @maximind5677
      @maximind5677 5 років тому

      You need to learn more calculus in order to properly understand gradient descent, at the moment if you know python you can create Linear Regression models

    • @valoredramack9117
      @valoredramack9117 5 років тому

      @@maximind5677 Your response is not specific enough, I already have a basic understanding of Calculus fundamentals as I explained, so my question is what else do I need to learn that I can't simple google in order to understand gradient descent? Gradient Descent doesn't seem that much more complicated than any other function or tangent equation from what I read.

  • @Randomiz8orinator
    @Randomiz8orinator 6 років тому +10

    siraj is definitely the best mentor

  • @Pingao2012
    @Pingao2012 4 роки тому

    Excellent. Thanks

  • @pranavsharma203
    @pranavsharma203 6 років тому

    Thanks siraj..do you know paresh raval....renowned indian actor and comedian

  • @collegeguide4882
    @collegeguide4882 6 років тому +26

    Love you sentdex !

  • @onyxpraisemedia7020
    @onyxpraisemedia7020 6 років тому

    Very helpful videos, thank you

  • @juancastillo9066
    @juancastillo9066 6 років тому +6

    "Cup it like a nice ... bowl" Lmao xD

  • @biargeamauri
    @biargeamauri 6 років тому

    Siraj congratulations!
    Great Job, It was a simple explanation and clear...

  • @jeanpaulwilliamsvillanueva606
    @jeanpaulwilliamsvillanueva606 6 років тому

    Thank you, I am new in this tecnical. I think I re-read theory about probability, calculus and other. Can you recommend me some books or platforms to reform these issues? please. Excellent video.

  • @AmriteshGaniger
    @AmriteshGaniger 5 років тому +2

    0:52 "It isn't or is it?"
    *Vsause music kicks in*

  • @rishobkumar8983
    @rishobkumar8983 6 років тому

    The video was really helpful man. Thanks a ton..

  • @ilozeet
    @ilozeet 6 років тому

    as he muscle mass goes up, hes hair gets less, more much DHT siraj, look into that, love you

  • @nigeldupaigel
    @nigeldupaigel 6 років тому

    Y = an estimate, first line you draw already was the estimated, but should be the average, because you didn’t apply sum of least squares for that

  • @paulthompson9668
    @paulthompson9668 6 років тому

    Siraj Raval
    Excellent introduction. Can you just keep building on this material?

  • @kalebbruwer
    @kalebbruwer 6 років тому

    These are some really good animations.

  • @trevor_idiot
    @trevor_idiot 5 років тому +1

    the memes are so cool I kept rewinding to read again

  • @AlanDeAnda1
    @AlanDeAnda1 6 років тому

    This stuff must be in my Economics school subjects program

  • @varungopal6272
    @varungopal6272 6 років тому

    U really make videos that are very useful

  • @kitgary
    @kitgary 6 років тому

    I am getting crazy about the Maths, it's so much harder than programming, I am thinking to quit my current job to learn it full time.

  • @zabilmaooz7780
    @zabilmaooz7780 4 роки тому

    Nice.. btw do you have any playlist in which you teach all the math required for ml? Or give me some references from which I could learn it?

    • @RoyalBengalCub
      @RoyalBengalCub 4 роки тому

      Hello!
      We are researchers in human-computer interaction (HCI) looking for people who have taken an initiative to recently learn Machine Learning on their own, for career, course or curiosity. Tell us here (www.surveymonkey.ca/r/SelfLearning_ML) about your experiences and any difficulties you faced while self-teaching ML and how you overcame them, and have a chance to win $50 giftcard.
      You can help this project by taking out 5-10 minutes to participate in our study. People from any major/background may participate.
      For more details, see here: www.surveymonkey.ca/r/SelfLearning_ML
      Please share this request with your colleagues or friends who fit this description. The survey will be open until July 20, 2020.

  • @ajcab819
    @ajcab819 5 років тому

    Omg you are better than most of my professors

  • @napalm_exe
    @napalm_exe 6 років тому

    Subscribed. Great Video!

  • @zakarie
    @zakarie 6 років тому +9

    Statistics and computer science can do cool things

  • @gessegoncalves6493
    @gessegoncalves6493 6 років тому

    Congratulations very good, your English is perfect, your videos are very informative
    From Brasil

  • @spayseghost
    @spayseghost 6 років тому

    wow this is what i have been waiting for .. great work id become a patron but, i allready am. maybe i raise my contribution

  • @ShadowParalyzer
    @ShadowParalyzer 6 років тому +5

    Question: What's the difference between probability and statistics? I've always thought that probability is a subclass of statistics.

    • @Canada3212
      @Canada3212 6 років тому +10

      Kiwimaru statistics is about what already happened (past and present), and making insights from that.. probability is about making predictions (future)

    • @YumekuiNeru
      @YumekuiNeru 5 років тому

      I suggest reading about it on e.g wikipedia rather than trusting random youtube comments

  • @ignaciodelamadrid
    @ignaciodelamadrid 6 років тому

    Siraj, learning machine learning with you is really easy. I really really love your content and thus I started supporting you on Patreon. Are you still posting content in that platform? I would love to know that in order to raise up my pledge to be able to have a direct conversation with you sometimes. My best wishes man and keep up the good work.

  • @anirudhkhanna8771
    @anirudhkhanna8771 6 років тому +3

    Cup it firmly in your hand.. like a nice... .. bowl - Siraj, 2018

  • @umairrehman4299
    @umairrehman4299 6 років тому

    Can you make a video on Kriging (KG) Method for parameter estimation?

  • @kylewattssurfing3266
    @kylewattssurfing3266 5 років тому

    Thanks really awesome thank you appreciate the time you're taken to educate and teach and share your knowledge man, thanks bro so awesome!