StatQuest: t-SNE, Clearly Explained

แชร์
ฝัง
  • เผยแพร่เมื่อ 27 ธ.ค. 2024

ความคิดเห็น • 749

  • @statquest
    @statquest  5 ปีที่แล้ว +73

    Corrections:
    6:17 I should have said that the blue points have twice the density of the purple points.
    7:08 There should be a 0.05 in the denominator, not a 0.5.
    Support StatQuest by buying my book The StatQuest Illustrated Guide to Machine Learning or a Study Guide or Merch!!! statquest.org/statquest-store/

    • @linweitao6470
      @linweitao6470 5 ปีที่แล้ว +1

      Thanks very much for the informative lecture and it is really helpful. UMAP is more and more popular now, could you explain it and compare with tSNE as well? Thanks in advance.

    • @statquest
      @statquest  5 ปีที่แล้ว +6

      @@linweitao6470 I should have a UMAP StatQuest ready in a few weeks. I'm working on it right now.

    • @linweitao6470
      @linweitao6470 5 ปีที่แล้ว +1

      @@statquest Thanks again!

    • @CompBioQuest
      @CompBioQuest 5 ปีที่แล้ว +2

      @@statquest UMAP is great, I dont know if it is more popular. There are more stringent reductions out there like ICA. I wonder the thoughts of Josh about it?

    • @statquest
      @statquest  5 ปีที่แล้ว +2

      @@CompBioQuest I guess it largely depends on the field. Right now, genetics and molecular biology are going bonkers over UMAP. However, ICA is very interesting. Thanks to your question, I found this article which is fascinating: gael-varoquaux.info/science/ica_vs_pca.html

  • @tuongminhquoc
    @tuongminhquoc 2 ปีที่แล้ว +7

    Thank you. I am not sure if you remember me from the PCA video. I have a job now. My job do not have high salary, but I could now support you by donating and thank you now. 😊

    • @statquest
      @statquest  2 ปีที่แล้ว +1

      WOW! Thank you so much. And congratulations on getting a job!!! HOORAY!!! TRIPLE BAM! :)

    • @tuongminhquoc
      @tuongminhquoc 2 ปีที่แล้ว +1

      @@statquest Keep doing great work sir! Also, it would be great if you could make a video about the comparation between clustering methods. 😁

    • @statquest
      @statquest  2 ปีที่แล้ว +1

      @@tuongminhquoc Thanks and I'll keep that in mind!

  • @abdulgadirhussein2244
    @abdulgadirhussein2244 4 ปีที่แล้ว +88

    I am always blown away by how you make statistics & machine learning algorithms so simple to understand and how you graciously share your knowldege. Keep up the great work man, you are awesome!

    • @statquest
      @statquest  4 ปีที่แล้ว +2

      Thank you very much! :)

  • @잠꾸러기-g1s
    @잠꾸러기-g1s 3 ปีที่แล้ว +23

    Whenever I find statistics technique I have never seen in scientific article, I always visit your channel. Thanks a lot!!

    • @statquest
      @statquest  3 ปีที่แล้ว +2

      Happy to help! :)

  • @veronikaberezhnaia248
    @veronikaberezhnaia248 3 ปีที่แล้ว +13

    I regret I can't put 1000 likes! I read about 20 articles about t-SNE, they are similar to one another, almost identical - and they don't get me closer to the point. But your video - I watched it 4 times (because the topic is hard, at least for me) with making some and drawing - but finally I understand how it works, up to the point that I can explain it to someone else. So many thanks to you!

    • @statquest
      @statquest  3 ปีที่แล้ว

      HOORAY!!! TRIPLE BAM! I'm glad the video was helpful. BAM! :)

  • @gustavomorais4489
    @gustavomorais4489 4 ปีที่แล้ว +14

    I never leave comments, but I really feel the need to thank you for being able to explain this in such a simple way

    • @statquest
      @statquest  4 ปีที่แล้ว +1

      Thank you! :)

  • @RezaRob3
    @RezaRob3 4 ปีที่แล้ว +5

    I'm writing this comment while having watched only half way into this video, which is pretty unusual for me!
    It is so clearly explained! I once glanced at the t-SNE paper and didn't understand it. If this is what it does then this is how things like this should be explained!
    Really, we need people explaining science like this! It's possible to read scientific papers, but what they fail to do is properly communicate the core idea to the reader so that the reader quickly grasps the big picture and the intent of the mathematical details without getting lost in the details.
    Frequently, even a missing definition can make reading papers much harder for non experts.

    • @statquest
      @statquest  4 ปีที่แล้ว +1

      I'm glad you liked this video so much! :)

  • @douglasaraujo9763
    @douglasaraujo9763 4 ปีที่แล้ว +112

    As entertaining as watching a Walt t-SNE movie!

    • @statquest
      @statquest  4 ปีที่แล้ว +15

      You made me laugh out loud! BAM! :)

    • @arenashawn772
      @arenashawn772 10 หลายเดือนก่อน +1

      Best stat-word-play of the year! 😂

  • @jjlian1670
    @jjlian1670 5 ปีที่แล้ว +12

    Josh is so far my favorite TH-camr that is able to explain complex stats concepts so smoothly.

    • @statquest
      @statquest  5 ปีที่แล้ว +1

      Thank you so much! :)

  • @gayathrikurada3315
    @gayathrikurada3315 4 ปีที่แล้ว +5

    Josh.. Your explanation is always "simple and easy to understand" even for layman.You are simply "The life Saviour" !!!
    Thank you so much :)

    • @statquest
      @statquest  4 ปีที่แล้ว +1

      Hooray! I'm glad my video was helpful. :)

  • @OnSightNoMore
    @OnSightNoMore 4 ปีที่แล้ว +7

    It's impressive how you managed to explain the essential concepts of this chain of algorithms in such a clear way! I'm sharing this video with my beginner fellows, who normally flee as soon as I say words like nearest-neighbor or stochastic.
    Thank you very much!

    • @statquest
      @statquest  4 ปีที่แล้ว

      Thank you very much! :)

    • @willykitheka7618
      @willykitheka7618 2 ปีที่แล้ว +2

      🤣🤣🤣🤣it's that terrifying?!? Barbara Oakley in her book, "a mind for numbers" called them zombies🤣🤣🤣

  • @kass8036
    @kass8036 7 ปีที่แล้ว +242

    I never knew machine learning could be as simple as... BAM

    • @thomasrad6296
      @thomasrad6296 4 ปีที่แล้ว +1

      Thats like the most important lesson.

    • @namimiable
      @namimiable 4 ปีที่แล้ว +2

      Double bam 💥

    • @kalyanben10
      @kalyanben10 4 ปีที่แล้ว +3

      Just a random comment so that someone can say triple bam

    • @kass8036
      @kass8036 4 ปีที่แล้ว +5

      Triple bam 💥

    • @birenpatel894
      @birenpatel894 3 ปีที่แล้ว +3

      hurayyyy we have made it to the END !!!

  • @sarangak.mahanta6168
    @sarangak.mahanta6168 3 ปีที่แล้ว +1

    The only educational channel which brings a smile to my face.

  • @nanopore-sequence
    @nanopore-sequence 4 ปีที่แล้ว +7

    I am a student in Japan.
    I'm not good at English, but it was very easy to understand and I learned a lot:)

  • @DoanQuocHoan
    @DoanQuocHoan 4 ปีที่แล้ว +3

    I was so confusing about t-SNE until I watched this. It's clear and very easy to understand! Thank you! Like your BAM. :D

  • @thedrunkprogrammer1474
    @thedrunkprogrammer1474 4 ปีที่แล้ว +1

    I really can't appreciate you enough for your videos.
    Books and blogs only make sense after I watch your videos!

    • @statquest
      @statquest  4 ปีที่แล้ว

      Thank you very much! :)

  • @Ravi5ingh
    @Ravi5ingh 4 ปีที่แล้ว +2

    It's rare to come across such a brilliant explanation.

    • @statquest
      @statquest  4 ปีที่แล้ว

      Thank you! :)

  • @atakanekiz
    @atakanekiz 5 ปีที่แล้ว +272

    Great explanations! Can you please do a video explaining UMAP and potentially how it compares to t-SNE? Thanks!

  • @edridgedsouza1170
    @edridgedsouza1170 4 ปีที่แล้ว +56

    "This is Josh Starmer, and you're watching Tisney Channel!"

    • @statquest
      @statquest  4 ปีที่แล้ว +10

      Triple BAM! :)

  • @Kmysiak1
    @Kmysiak1 4 ปีที่แล้ว +1

    This explanation almost makes tSME sound like a clustering technique not a reduction technique..... That said, this was by far the best explanation I've heard to date.

    • @statquest
      @statquest  4 ปีที่แล้ว +2

      That's a good observation. In many ways t-SNE is a hybrid method that reduces dimensions by clustering.

    • @Kmysiak1
      @Kmysiak1 4 ปีที่แล้ว +1

      @@statquest Now if you can explain how to interpret a tSME plot. This would help immensely as it's virtually impossible to determine the correct perplexity number without understanding how to interpret the plot. This seems like one of those "blackbox" methods which we just trust. Keep up the great work!

  • @snackbob100
    @snackbob100 4 ปีที่แล้ว +4

    Josh, i literally love your videos, they are really helping me get through my ADV CS degree. I am going to buy one of your shirts, and wear it on campus as a thank you!

    • @statquest
      @statquest  4 ปีที่แล้ว +1

      That would be awesome!!! Thank you very much! :)

  • @shanthinagasubramanian2866
    @shanthinagasubramanian2866 2 ปีที่แล้ว +1

    Very nice way of teaching ! ML concepts CLEARLY EXPLAINED and BAM adds lot of curiosity in the videos :) Thanks for your videos. And not to forget your songs are really nice :)

  • @alvarovs89
    @alvarovs89 2 ปีที่แล้ว +1

    Just hear about t-SNE and I did not quite understand how it works so I crossed my fingers hoping that josh did a video of this and of course he did!! haha
    I have my popcorn ready to enjoy this video :)

  • @saiakhil4751
    @saiakhil4751 3 ปีที่แล้ว +3

    Why I couldn't stop bamming the like button??!! You're the best Josh!!

  • @nikhilgoparapu8183
    @nikhilgoparapu8183 4 ปีที่แล้ว +2

    Very clearly explained!
    Loved the way you explained such a complicated concept so intuitively.
    Thank you.

    • @statquest
      @statquest  4 ปีที่แล้ว

      Glad it was helpful!

  • @nguyenthituyetnhung1780
    @nguyenthituyetnhung1780 8 หลายเดือนก่อน +1

    thanks for your great explaination. I just wonder from 5:00 - 5:45, Why when you plot the distance on the normal curve the red and the orange is on different sides of normal curve. I thought distance didn't have direction. Can you please explain more detail about this different direction of the red and orange?

    • @statquest
      @statquest  8 หลายเดือนก่อน

      The normal curve is symmetrical, so we can puts the dots on either side. In this case, I used both sides so that not all the dots would overlap.

    • @nguyenthituyetnhung1780
      @nguyenthituyetnhung1780 8 หลายเดือนก่อน +1

      @@statquest yeah, i understood. Because we take p as similarities values so right or left is the same. Thanks a lot. Your videos help me a lot in my machine learning studying.

  • @camilaarcu2254
    @camilaarcu2254 3 ปีที่แล้ว +1

    You are incredible, Josh Starmer!! I loved this

    • @statquest
      @statquest  3 ปีที่แล้ว

      Thank you! :)

  • @ramnarasimhan1499
    @ramnarasimhan1499 7 ปีที่แล้ว +1

    Fantastic video. I really appreciate all the slides that you made to get the animation effect. It really helped. Possibly the best explanation of t-SNE around. Keep up the good work.

  • @abhaymathur9332
    @abhaymathur9332 5 ปีที่แล้ว

    this is such an awesome explanation of tsne that i dont need to watch any other video or read any other website/book. I dont think there can be a better explanation. Superlike.

  • @jannelis2845
    @jannelis2845 5 ปีที่แล้ว +2

    Very well explained ! Your video was recommended to us by our professors at ETH-Zürich.:)

  • @soumitachel3844
    @soumitachel3844 4 ปีที่แล้ว +1

    Hello Josh, thank you for coming with such incredible videos. Data scientist’s life becomes easy.😬

    • @statquest
      @statquest  4 ปีที่แล้ว

      Thank you! :)

    • @soumitachel3844
      @soumitachel3844 4 ปีที่แล้ว

      StatQuest with Josh Starmer Hi a request to do a tutorial of UMAP.

  • @RaketeTapete
    @RaketeTapete 5 ปีที่แล้ว +2

    Came here for understanding the t-SNE plots used in single cell transcriptomics - which I finally did, thanks! Overall, you helped me out already plenty of times!
    To display cells in during cell fate transition/acquisition e.g. different time points during neurodevelopment, often pseudo-temporal ordering is used.
    Since scRNA seq is becoming more and more popular, this might be a good next topic

    • @erazael
      @erazael 5 ปีที่แล้ว

      Same here, and I did not expect to understand so fast and clearly!

  • @srishtikumar5544
    @srishtikumar5544 4 ปีที่แล้ว +1

    Excellently explained! I really like your simple, clear, concise explanation - those 3 factors make a world of difference. And, great animations.

    • @statquest
      @statquest  4 ปีที่แล้ว

      Awesome, thank you!

  • @veeek8
    @veeek8 2 ปีที่แล้ว +1

    Brilliant explanation, this has been bugging me all day, thank you!!

    • @statquest
      @statquest  2 ปีที่แล้ว

      Glad it helped!

  • @scifimoviesinparts3837
    @scifimoviesinparts3837 4 ปีที่แล้ว +1

    The Best tutorial and explanation for TSNE so far! It's of great help! Thanks a lot!

  • @pierrefoidart5368
    @pierrefoidart5368 4 ปีที่แล้ว

    Thanks a lot!! These videos are much more clear than any article!
    A video explaining UMAP (related to t-SNE) would be awesome !

    • @statquest
      @statquest  4 ปีที่แล้ว

      I'm working on UMAP. For now, however, know that it is almost 100% the same as t-SNE. The differences are very subtle.

  • @imamalva5603
    @imamalva5603 4 ปีที่แล้ว +1

    you are the hero, keep explaining complex thing into simple. thankss

    • @statquest
      @statquest  4 ปีที่แล้ว

      Thank you! :)

  • @lilmoesk899
    @lilmoesk899 7 ปีที่แล้ว

    Great as always. I've heard of t-SNE before, but this was my first real introduction to it. Definitely want to go look at some more resources now.

  • @sagar_bro
    @sagar_bro 4 ปีที่แล้ว +4

    I just love the way you start all your videos! Stat-Questtttttt :)

  • @parvezrafi4098
    @parvezrafi4098 6 ปีที่แล้ว

    Thanks a lot. I really struggled to understand the concept first time I came across it in a book. Your video helped a lot. Great job!

  • @vishnumuralidharan9858
    @vishnumuralidharan9858 ปีที่แล้ว +2

    Hi Josh, I can't thank you enough for how much I have benefitted from your videos even though I do data science as part of my day job. Thank you so much for sharing your knowledge!
    One request for a video: could you do a video of when to use which methods / models in a typical data science problem? Much appreciated.

    • @statquest
      @statquest  ปีที่แล้ว +1

      That's a great idea.

  • @ImmutableHash
    @ImmutableHash 6 ปีที่แล้ว

    Awesome explanation, thank you so much! I read a few papers/books multiple times and barely have a clue, but with your vid I understand the concept just by watching it once!

  • @bright1402
    @bright1402 6 ปีที่แล้ว

    This is the best video for t-SNE that I have ever seen. Thanks a lot, man

  • @chaitanyakulkarni243
    @chaitanyakulkarni243 3 ปีที่แล้ว +2

    Wish I could *Triple Bam* like this video! Such a simple explanation. Thanks a lot Josh :-)

    • @statquest
      @statquest  3 ปีที่แล้ว +1

      Glad you liked it!

  • @redaaitouahmed8250
    @redaaitouahmed8250 4 ปีที่แล้ว +2

    Super Mega BAM !! So great at what you do as always ... Tons of love sent your way ! Keep up the amazing work :D

    • @statquest
      @statquest  4 ปีที่แล้ว +1

      Thanks so much!!

  • @NirajKumar-hq2rj
    @NirajKumar-hq2rj 6 ปีที่แล้ว

    excellent explanation , this intuition helps to follow maths behind t-SNE

  • @chauphamminh1121
    @chauphamminh1121 5 ปีที่แล้ว

    You make a complex idea becomes so simple and understanding ! Great video. Thanks a lot

  • @abhijitkumbhar1
    @abhijitkumbhar1 ปีที่แล้ว +1

    Difficult concept made so simple. Just brilliant!!!!

    • @statquest
      @statquest  ปีที่แล้ว

      Thanks a lot 😊!

  • @MrCEO-jw1vm
    @MrCEO-jw1vm 6 หลายเดือนก่อน +1

    Thank you so much for this great resource and how much investment you have made into it. I have understood this well.

    • @statquest
      @statquest  6 หลายเดือนก่อน

      Glad it was helpful!

  • @octour
    @octour 5 ปีที่แล้ว

    Thanks for such a clear explanation. You know, your channel already in the top list for me and very soon I'll watch all your videos..

  • @reedayoungblood
    @reedayoungblood 4 ปีที่แล้ว +2

    Great video - thank you! One small insertion that I think would improve it: at ~2:07, right after showing what projecting on to the X or Y axis would look like, show one more example of projecting onto an arbitrary line to try to retain as much variance as possible (basically PCA). I think this could be done in 15-20 seconds, and would be helpful in comparing t-SNE to one of its most popular alternatives, which is helpful in deciding *when* to use an algorithm - one of the hardest things for beginners like myself.

    • @statquest
      @statquest  4 ปีที่แล้ว

      Thanks for the tip!

  • @carlosalfonso5829
    @carlosalfonso5829 6 ปีที่แล้ว +1

    OH God, this is a great explanation, as Radel mention below, it would be nice to have an extended video of the algorithm as the one from PCA!!

    • @statquest
      @statquest  6 ปีที่แล้ว

      Thank you! Yes, one day I'll break the actual equations down and do "step-by-step" explanation of t-SNE.

    • @niteshturaga
      @niteshturaga 6 ปีที่แล้ว

      Looking forward to this.

  • @deepika3389
    @deepika3389 3 ปีที่แล้ว +1

    Kudos, I understood so effortlessly....tripple BAM!!!

  • @thoniageo
    @thoniageo 3 ปีที่แล้ว +1

    i am a huge fan of this channel! greetings from brazil ^^

    • @statquest
      @statquest  3 ปีที่แล้ว

      Muito obrigado! :)

  • @RajeshSharma-bd5zo
    @RajeshSharma-bd5zo 4 ปีที่แล้ว +1

    One word reaction after watching this video --> AWESOME!!

    • @statquest
      @statquest  4 ปีที่แล้ว

      Thank you so much 😀!

  • @axeleriksson8978
    @axeleriksson8978 7 ปีที่แล้ว +45

    Hey, love your videos!
    Just a typo but it should be 0.05 on the values to the right at 07:19. Confused me for a second so might clear things up for others.

  • @petersu4869
    @petersu4869 4 ปีที่แล้ว +2

    "Bam, I made that terminology up" :D :D , great vid, keep up the good work.

    • @statquest
      @statquest  4 ปีที่แล้ว

      Thanks! 😁

  • @prateekyadav7679
    @prateekyadav7679 4 ปีที่แล้ว

    I never thought I'd not understand a statquest video! :(

    • @statquest
      @statquest  4 ปีที่แล้ว

      Bummer. What time point was confusing?

  • @UxJoy
    @UxJoy 4 ปีที่แล้ว +1

    Dude this is super clear. Love the content! BAM

    • @statquest
      @statquest  4 ปีที่แล้ว

      Thank you very much! :)

  • @hulaalol
    @hulaalol 3 ปีที่แล้ว +1

    thank you so much for this nice explanation. will help me a lot in my exams

    • @statquest
      @statquest  3 ปีที่แล้ว

      Glad to hear that!

  • @benw4361
    @benw4361 5 ปีที่แล้ว +1

    Love the vid. I was wondering how tsne works and you broke it down great and the explanation for the t distribution was short and to the point.

    • @statquest
      @statquest  5 ปีที่แล้ว +1

      Thank you! :)

  • @vikramreddy3699
    @vikramreddy3699 4 ปีที่แล้ว

    Thank you Josh . I love the way you present concepts with simple examples.
    Could you please explain how you decided the red dot directions to the left, where as the orange on right side @5:30 ?

    • @statquest
      @statquest  4 ปีที่แล้ว

      It doesn't matter what side of the curve the points are on, since the distance from the y-axis values on the curve will be the same (normal curves are symmetrical). However, in order for the points to be easily seen, I spread them out on different sides rather than piling them all up on top of each other.

    • @vikramreddy3699
      @vikramreddy3699 4 ปีที่แล้ว +1

      @@statquest Thank you again

  • @mic9657
    @mic9657 ปีที่แล้ว +1

    Amazing work! perfectly explained!!!

  • @rgarthwood3881
    @rgarthwood3881 5 ปีที่แล้ว +20

    "Clearly Expalined" indeed!

  • @arthurlee4294
    @arthurlee4294 4 ปีที่แล้ว +1

    hi,i have a question at 8:44,why symmetric probability is Pij = (Pi|j + Pj|i)/2N and not Pij = (Pi|j + Pj|i)/2 ? why there is a N? THANK YOU!

    • @statquest
      @statquest  4 ปีที่แล้ว

      I have no idea.

  • @DaniTeba
    @DaniTeba 4 ปีที่แล้ว +1

    Thank you a lot for the video Josh.
    Let me point something out, and by minute 10:40, it looks like that t-sne perform a sort of the matrix, instead of minimizing the loss function by gradient descent.

    • @statquest
      @statquest  4 ปีที่แล้ว +1

      Good point. I represented it as a matrix because, internally, all of the similarity scores are maintained that way.

  • @somethingandapie
    @somethingandapie 6 ปีที่แล้ว +1

    Subscribed because that intro gave me life!

    • @statquest
      @statquest  6 ปีที่แล้ว

      Ha!!! Thanks! :)

  • @arenashawn772
    @arenashawn772 10 หลายเดือนก่อน +1

    t-SNE in concept is a little dense to me so I am watching this video multiple times to think about the nitty gritty of it… I have three perhaps very naive questions so far: 1) with really high dimensional feature space for some data, how do t-SNE algorithms decide how many dimensions to use for the simplified data? In PCA it can be specified by inspecting the variance of data in each of the components to decide that new feature’s “contribution” in grouping/separating the datapoints, is there a similar measure that is used to decide how many dimensions are used in t-SNE? 2) Why is it only used as a visualization technique and not a true dimension-reduction method for data pre-processing in machine learning pipelines? 3) is it possible that the data do not converge in low dimensional space (i.e., you just could not move the second matrix so that it is similar enough to the first one)?
    I dug out the original 2008 paper from SkLearn citation and as usual was amazed by how you explained the fairly abstract idea in section 2 of the paper in a mere 20-minute long unhurried video, down to the analogy of the repelling and attraction of mapped data in the low dimensional space (the original paper interpreted the gradient decent method used to locate the low dimensional mapping of points as “springs between every point and all other points”) - no important detail is lost in your video yet they are organized in such a way that they follow a clear logic and do not overwhelm. That is mastery of the art of elucidation ❤
    Thanks as always for digesting these complicated items for the benefit of the students and present them in simplified yet informative ways, as always!

    • @statquest
      @statquest  10 หลายเดือนก่อน

      Thank you very much! For t-SNE, I'm pretty sure it's always used to generate a 2 (or at most 3) dimensional graph that can be visualized. This is because, unlike PCA, where the axes (or PCs) actually represent something (the directions of the most variance), the axes in t-SNE are completely arbitrary. So there's no way to quantify or rank the axes in order of importance. And it is probably possible to have the low dimensional graph fail to converge. That said, if you'd like more details on t-SNE, check out my videos on UMAP - a related technique that is a little more popular: th-cam.com/video/eN0wFzBA4Sc/w-d-xo.html and th-cam.com/video/jth4kEvJ3P8/w-d-xo.html

  • @abcdefghi2650
    @abcdefghi2650 2 ปีที่แล้ว +1

    Great videos! Great channel! Big thumbs UP!

  • @DumplingWarrior
    @DumplingWarrior 4 หลายเดือนก่อน +1

    Hi Josh, great videos as always! I'm not sure if there's a video about this already, but could you do one with all the clustering or classification or dimensionality reduction methods compiled together and then compare their differences and similarities and talk about situations when we should use which? For example, after looking at many of the videos, I think I'm already a little lost on if I should use PCA or MDS or t-SNE on my data. Ty.

    • @statquest
      @statquest  4 หลายเดือนก่อน

      Thanks! I'll keep that in mind.

  • @sudortd
    @sudortd ปีที่แล้ว +1

    I need to watch 3 more times to fully understand. TRIPLE BAM!!!

  • @precisionimmunologyincubat2315
    @precisionimmunologyincubat2315 5 ปีที่แล้ว +2

    Thank you so much! Right now everyone in our department (Systems Genetics at NYU Langone) is using UMAP. There aren't many great videos about it - it would be awesome if you could help us understand what all the hype is about!

    • @statquest
      @statquest  5 ปีที่แล้ว +2

      UMAP is on the to-do list. I hope to get to it in the spring.

  • @leixiao169
    @leixiao169 4 ปีที่แล้ว +1

    your explanation is very very good! thanks!!!

    • @statquest
      @statquest  4 ปีที่แล้ว

      Thank you! :)

  • @p.b.3697
    @p.b.3697 5 ปีที่แล้ว +1

    Thank you very much Josh . You made it easier to understand.

    • @statquest
      @statquest  5 ปีที่แล้ว

      Hooray! I'm glad the video was helpful! :)

  • @Elmirgtr
    @Elmirgtr 6 ปีที่แล้ว +6

    Your speak like Kevin from The Office. Great explanation, thanks a lot:)

  • @Antony25rages
    @Antony25rages 7 หลายเดือนก่อน

    Hi @statquest - At 6:06 you mention that we scale the similarity scores, and at 8:29 we discuss again that the similarity would be different for those 2 points from different clusters. It should be same right post scaling?

    • @statquest
      @statquest  7 หลายเดือนก่อน +1

      Maybe. In this example, yes. But if each cluster had different numbers of points in them, I'm not sure they would.

    • @Antony25rages
      @Antony25rages 7 หลายเดือนก่อน +1

      @@statquest got it, will check this and post my findings

  • @HR-yd5ib
    @HR-yd5ib 7 ปีที่แล้ว +19

    Excellent video! Perhaps you could add another video where you go through the actual algorithm and how the moves is actually computed.

  • @sandipansarkar9211
    @sandipansarkar9211 4 ปีที่แล้ว +1

    great explanation especially for beginners.Thanks

    • @statquest
      @statquest  4 ปีที่แล้ว

      Thank you! :)

  • @Bedivine777angelprayer
    @Bedivine777angelprayer ปีที่แล้ว +1

    Thanks really great videos understood concepts so well

    • @statquest
      @statquest  ปีที่แล้ว

      Glad it was helpful!

  • @nathalychicaizacabezas3055
    @nathalychicaizacabezas3055 4 ปีที่แล้ว +1

    I am at the intro and love it already!

  • @Patrick881199
    @Patrick881199 4 ปีที่แล้ว +1

    Hi, Josh, if we want to get the "similarity score", why don't we simply use the distance between points, instead of using normal curve to calculate the length between point and curve?

    • @statquest
      @statquest  4 ปีที่แล้ว

      The normal curve forces the distances to focus on other points that are relatively close.

  • @abarnaabalakrishnan1862
    @abarnaabalakrishnan1862 7 ปีที่แล้ว

    VERY CLEAR EXPLANATIONS :) THANK YOU FOR ALL YOUR VIDEOS

  • @yunfan7034
    @yunfan7034 4 ปีที่แล้ว

    Thank you for this tutorial. I have a question. Can you please help me? Thank you. On 5:37 , it measures the "distance" to the curve to get similarity scores. Since "distance" is always positive. How to make all red point on the left side? (it is negative, but distance is positive). All orange points are the right side.( positive, since distance is positive, I can understand this part)

    • @statquest
      @statquest  4 ปีที่แล้ว +1

      Because the minimum y-axis value for the normal distribution is > 0. the distance, in terms of the y-axis, is always positive, regardless of whether or not a point is on the left or right side of the peak of the curve.

  • @Tony-Man
    @Tony-Man 9 หลายเดือนก่อน

    Hi Josh, quality content! This channel continuously helps me to understand the idea behind so that the dry textbook explanations actually make sense. I still have a question. When you calculate the unscaled similarity score, how do you exactly determine the width of your guassian? I get it in the example that we already know the cluster. If I only want to visualize the data without having pre-defined clusters, what happens then?

    • @statquest
      @statquest  9 หลายเดือนก่อน

      I talk more about the details of t-SNE and how it works in my videos on UMAP: th-cam.com/video/eN0wFzBA4Sc/w-d-xo.html and th-cam.com/video/jth4kEvJ3P8/w-d-xo.html

  • @carlmemes9763
    @carlmemes9763 3 ปีที่แล้ว +1

    Thanks for this wonderful video❤️

    • @statquest
      @statquest  3 ปีที่แล้ว

      Glad you enjoyed it!

  • @cyrilbaudrillart9690
    @cyrilbaudrillart9690 4 ปีที่แล้ว

    Great explanation! Thank you so much... I think their is a typo @7:08. Oh oh... On upper part, sum of all scores is 0.24+0.5 instead of 0.24+ 0.05. BAM. Same mistake on the other equation with same denominator. Double BAM. Results are correct. Triple BAM :-)

    • @statquest
      @statquest  4 ปีที่แล้ว +1

      Thanks! I added that note to the pinned comment.

  • @Underscore_1234
    @Underscore_1234 3 ปีที่แล้ว

    Super clear. Is the small move carresponding to some learning rate multiplying the gradient of some distance between the expected distance matrix and the one we have?

    • @statquest
      @statquest  3 ปีที่แล้ว

      I believe so.

  • @notallama1868
    @notallama1868 2 ปีที่แล้ว

    But how do you get the normal curve at 4:34? As far as I can tell, we only have the mean (the point of interest), which (I think) isn't enough to calculate a normal distribution. Are we just picking a random normal distribution that's centered on the point of interest? And how do you put multidimensional data into a normal distribution anyway?

    • @statquest
      @statquest  2 ปีที่แล้ว +1

      The width of the curve is determined by the perplexity parameter. For details, see my videos on UMAP: th-cam.com/video/eN0wFzBA4Sc/w-d-xo.html and th-cam.com/video/jth4kEvJ3P8/w-d-xo.html

  • @daaronr
    @daaronr 3 ปีที่แล้ว

    Love it! A few things could still be clarified (please?):
    At 07:40, which vector of distances must add up to 1 after scaling? The sum of distances from each point to all other points (regardless of cluster)?

  • @govamurali2309
    @govamurali2309 3 ปีที่แล้ว

    @josh: Amazing videos..BTW @5:12 how do we decide that the orange dots goto the right of the bell curve? Why not to the left side of the bell curve?

    • @statquest
      @statquest  3 ปีที่แล้ว +1

      It doesn't matter. The curve is symmetrical.

    • @govamurali2309
      @govamurali2309 3 ปีที่แล้ว +1

      @@statquest Thank you Josh..please continue with the statquests..you are doing mankind a huge help!!!

  • @simonandrews5604
    @simonandrews5604 5 ปีที่แล้ว

    Incredibly helpful and well presented. Thank you.

  • @jarosawbachnio3753
    @jarosawbachnio3753 4 ปีที่แล้ว +1

    Hi Josh, great video, many thanks! Anyway, I still don't get how do you determine the distribution properties (like standard deviation) for calculating unscaled similarity between two points. When you introduced half as dense cluster as the others, you used normal distribution with standard deviation doubled, what is quite intuitve. But you knew that this cluster is just half as dense as the others. The question is, how to know the properties of these distribution curves?

    • @statquest
      @statquest  4 ปีที่แล้ว

      You estimate it from the data.

  • @debajitbhowmick7079
    @debajitbhowmick7079 3 ปีที่แล้ว

    1. In Flow Cytometry we use median for almost all data analysis because it best describes the central tendency of the data. Is geo mean anyway better describe Flow Cytometry data or geomean is better for some types of Flow Cytometry experiments?
    2. What are the drawbacks of downsampling? If there are any way to identify when to avoid downsampling?
    3. What is the batch effect? How to identify and remove it? What is the basic principle of identification? What are the strategies to avoid begin with?

    • @statquest
      @statquest  3 ปีที่แล้ว

      Great questions!

  • @maxdesancha6025
    @maxdesancha6025 3 ปีที่แล้ว +1

    Just out of curiosity.... ....are there any plans to do a video on trajectory analysis? I'm doing an analysis on whether the floating properties of ducks and wood can be used to predict the outcome of being a witch or not.

    • @statquest
      @statquest  3 ปีที่แล้ว +1

      Whatever your model, it will probably improve if you incorporate the average airspeed of swallow.

  • @davidm7765
    @davidm7765 3 ปีที่แล้ว +1

    Excellent work, thank you !!

  • @chiragshetty3231
    @chiragshetty3231 4 ปีที่แล้ว +1

    Excellent video.
    But I didn't understand why t-distribution is used to compute similarities in low dimension but Gaussian is used to compute similarities in a higher dimension? Why can't we use t-distribution for both

    • @statquest
      @statquest  4 ปีที่แล้ว +1

      I believe the original SNE algorithm used normal distributions for both. however, that resulted in the low-dimensional clusters to be too compact. So the t-distribution, which has fatter tails, was added to spread things out a little more in low dimensions.

    • @chiragshetty3231
      @chiragshetty3231 4 ปีที่แล้ว +1

      @@statquest Thanks, I love how you reply to all the queries on your videos.

  • @daaronr
    @daaronr 3 ปีที่แล้ว

    Also, 10:40: How are the points (initally) ordered in the matrix to the LEFT? Does the Blue/Red/Yellow on the axes of this matrix on the left mean anything or is that a mistake?

    • @statquest
      @statquest  3 ปีที่แล้ว

      I just ordered things by cluster because that was easiest for me, but the "true" ordering is done without knowing the clustering.

  • @BusinessScience
    @BusinessScience 5 ปีที่แล้ว +2

    Hey, love your videos! We are actually using it to help explain key concepts in our application-focused courses. I'd love to see UMAP (similar to t-SNE), which is a bit more scalable.

    • @statquest
      @statquest  5 ปีที่แล้ว +3

      Thank you so much! It's on the to-do list. :)

    • @BusinessScience
      @BusinessScience 5 ปีที่แล้ว +1

      @@statquest Awesome! I'm using your content in my courses - Students love it. PCA, K-Means, & t-SNE. Will be using your ML videos as well. Your explanations are the best!

  • @henkhbit5748
    @henkhbit5748 4 ปีที่แล้ว

    Great, never heard of t-sne. Is it only for visualisation purposes? In PCA points are clustered based on the correlations. Do you have also an analogy with the loadings of the features like in PCA?

    • @statquest
      @statquest  4 ปีที่แล้ว +1

      It's only for visualization. It does not have the equivalent of loading scores in PCA.

  • @MathPhysicsFunwithGus
    @MathPhysicsFunwithGus ปีที่แล้ว +1

    This is a great explanation thank you!

    • @statquest
      @statquest  ปีที่แล้ว +1

      Glad you enjoyed it!