Backpropagation Details Pt. 1: Optimizing 3 parameters simultaneously.

Поделиться
HTML-код
  • Опубликовано: 18 ноя 2024

Комментарии • 297

  • @statquest
    @statquest  3 года назад +12

    The full Neural Networks playlist, from the basics to deep learning, is here: ruclips.net/video/CqOfi41LfDw/видео.html
    Support StatQuest by buying my book The StatQuest Illustrated Guide to Machine Learning or a Study Guide or Merch!!! statquest.org/statquest-store/

    • @sahanamd707
      @sahanamd707 2 года назад

      In neural network, does the gradient for parameters are calculated parallel?
      For example: when I start with finding gradient for all the 7 parameters, do I calculate all 7 parameters simultaneously by taking the previous iteration values or, first I calculate the bias gradient and get the new bias, then calculate predicted value by new bias and then calculate gradient for w3 ? And so on till w1 ?

    • @statquest
      @statquest  2 года назад +2

      @@sahanamd707 Everything is done at the same time.

    • @sahanamd707
      @sahanamd707 2 года назад +1

      Thank you

  • @chaitanyasharma6270
    @chaitanyasharma6270 3 года назад +85

    the way you explain things,so patiently and in depth, i feel 200% more confident in the topic afterwards

  • @joserobertopacheco298
    @joserobertopacheco298 Год назад +16

    I'm writing from Brazil. This channel's playlist about neural networks is a masterpiece.

  • @KenJee_ds
    @KenJee_ds 4 года назад +123

    I wish I had this when I was first learning backpropagation! Can I "work my way backward" with this knowledge haha

    • @statquest
      @statquest  4 года назад +24

      BAM! :)

    • @romanrandall2106
      @romanrandall2106 3 года назад

      Pro tip: you can watch movies on flixzone. Me and my gf have been using it for watching lots of of movies lately.

    • @amoszahir7346
      @amoszahir7346 3 года назад

      @Roman Randall Definitely, have been using Flixzone for years myself :)

    • @rajeevradnair
      @rajeevradnair 3 года назад

      haha good one !!

    • @eduardbenedic9844
      @eduardbenedic9844 2 года назад +1

      @Roman Randall and @Amos Zahir are bots but nice one

  • @TheAkiller101
    @TheAkiller101 3 года назад +6

    I really like the medieval guitar sound you added when you said "fancy notation" , you effort can really be seen in the little details

  • @shafir360
    @shafir360 Год назад +10

    I am watching all of these eventhough i already graduated with masters with focus on machine learning and deep learning. its actually amazing how much I am learning even as a intermediate student.

  • @victorreloadedCHANEL
    @victorreloadedCHANEL Год назад +8

    We all should buy his book, he deserves it given the quality of these videos!!

    • @statquest
      @statquest  Год назад

      Thank you!!! :)

    • @peki_ooooooo
      @peki_ooooooo Год назад +1

      yes!

    • @MultiSamarjit
      @MultiSamarjit 8 месяцев назад

      ​@@statquest
      Hey man,
      just bought your book,will be arriving in a few days via amazon.All these topics are covered right?

    • @statquest
      @statquest  8 месяцев назад

      @@MultiSamarjit The basics of neural networks and backpropagation are covered. The other topics are listed here: statquest.org/statquest-store/

  • @erenplayzmc9452
    @erenplayzmc9452 8 месяцев назад +2

    OMG THE HAPPINESS I WAS FEELING WHEN I UNDERSTOOD EVERYTHING, you seriously are a really good teacher.

  • @mattduchene66
    @mattduchene66 6 месяцев назад +1

    Despite the simple explanations, these videos continuously make me doubt my mathematical abilities for about 15 minutes. But without fail, there’ll be a DOUBLE BAM! out of left field and suddenly everything’s clear in my head. Thank you! You’re doing God’s work.

  • @arindammitra2293
    @arindammitra2293 3 года назад +13

    Triple BAM (Explanation)+Triple BAM (Animations)......
    You are a very great teacher Josh Starmer :) :)

  • @averagecandy2581
    @averagecandy2581 10 месяцев назад +1

    The details are just out of this world. Amazing. Breath-taking and short of words.

  • @georgeshibley9529
    @georgeshibley9529 4 года назад +22

    One of these days I'd love to see you do a NN to watch the process you produced on these videos get lined up with some code, maybe python or R. It's incredible work you do, hell you are helping me survive my masters program. If you put it up, I'd trust the content. Thank you for all your hard work

    • @statquest
      @statquest  4 года назад +5

      Thank you! And good luck with your masters degree.

  • @vusalaalakbarova7378
    @vusalaalakbarova7378 2 года назад +6

    Thanks Josh for these videos, I passed my data mining exam by watching your videos, now preparing for the ML exam. Your explanation is brilliant, I learn topics of 3 lectures with these 18 minutes videos. Please continue to publish such valuable content, you save lives of many people like me.

    • @statquest
      @statquest  2 года назад

      Thank you and good luck with your exam! Let me know how it goes.

    • @vusalaalakbarova7378
      @vusalaalakbarova7378 2 года назад

      @@statquest Josh, are you planning to make a video about batch normalization?

    • @statquest
      @statquest  2 года назад

      @@vusalaalakbarova7378 Not soon. Currently I'm working on a series of videos about how to build neural networks with pytorch and pytorch_lightning.

  • @maayanmagenheim441
    @maayanmagenheim441 3 года назад +3

    I'm a student for CS at the Hebrew University of Jerusalem, study right now IML course. Your lectures so help me and my friends, and I really want to thank you. You're a great & funny teacher and your lessons are a perfect example to how to teach at the 21 century. Tnx again

    • @statquest
      @statquest  3 года назад

      Wow! Thank you very much! BAM! :)

  • @DharmendraKumar-DS
    @DharmendraKumar-DS Год назад +2

    How the heck do you have this much understanding in each concept...you are irreplaceable.

  • @magabosc2451
    @magabosc2451 4 месяца назад +2

    BAM !!! I'm doing my PHD in this field, and it is the BEST serie of videos that I have watched since the bigenning of my study ! Thank you so much for that :D

    • @statquest
      @statquest  4 месяца назад

      Thanks and good luck!

  • @anshuljain2258
    @anshuljain2258 7 месяцев назад +1

    Such hard work. Thank you Josh, you are helping generations with this + all your videos. Step by step learning with examples is the right way to learn anything !

  • @rohanmishra3115
    @rohanmishra3115 2 года назад +8

    What a great explanation to such complex topic. I can't imagine the amount of effort you put in to create such detailed videos along with spoken text. One of the best youtube channel I have ever come across ! Hats off to you .. Don't BAM me :)

  • @voyam
    @voyam 5 месяцев назад +2

    Had to watch 17:09 at least ten times. But now I get the most dificult part: the orange and blue curves, represent... the orange and blue curves. Without that, I would be completely lost 😆.
    Thanks for the hard work. Amazing series!

    • @statquest
      @statquest  5 месяцев назад

      I'm glad you figured it out! :)

    • @eren_deniz
      @eren_deniz 11 дней назад

      hahahaha

  • @ileshdhall
    @ileshdhall Месяц назад +1

    wow! WoW! WOW!, I have always been scared of math, cus it took me hell lot of time to understand, but you just explain it as smooth as butter, Thanks a lot really!!

    • @statquest
      @statquest  Месяц назад

      Thank you very much!

  • @blueeyessti
    @blueeyessti 2 месяца назад +1

    These videos are so much better than 3blue1brown, he starts with complicated analogies and examples and then delves into heavy math whereas this simplifies the problem using simpler examples and works through all the small steps

  • @nonalcoho
    @nonalcoho 4 года назад +15

    BAMMMMMMM!
    I like the animation in the last part and the music with Fan~cy notation lol

  • @wliw3034
    @wliw3034 3 года назад +1

    You are One of the Best Content Creator I have ever Seen.

  • @mortyk182
    @mortyk182 5 месяцев назад +1

    woah this was some amazing teaching skills sir, you're totally gifted with that

  • @tagoreji2143
    @tagoreji2143 2 года назад +1

    A Brief Indepth Explanation.Thank you Sir

  • @Viezieg
    @Viezieg 2 года назад +2

    thank you so much for these videos. i hated math back in high school, but now in my mid 20's i would rather do math than play video games. all thanks to your tutorials

    • @statquest
      @statquest  2 года назад

      Wow! That's awesome! Thank you!

  • @vladimirfokow6420
    @vladimirfokow6420 Год назад +1

    Thank you for your clear explanations with the simple example! Great work, and very useful.

  • @ericchao3017
    @ericchao3017 2 года назад +4

    Really loving these videos, thank you so much for your work Josh

  • @flyawayhome3
    @flyawayhome3 6 часов назад +1

    The little harpsichord really tickled me haha, love it

  • @Vanadium404
    @Vanadium404 Год назад +3

    This NN series is so underrated just 124K I mean come on

  • @starkarabil9260
    @starkarabil9260 3 года назад +3

    that was exactly what I needed. It would be great if you could 'also' do an application through one of Python libraries in order to show a real application by scripting with using this knowledge.

    • @statquest
      @statquest  3 года назад

      Thanks! I would like to do that.

  • @Tapsthequant
    @Tapsthequant 3 года назад +4

    You make this stuff so accessible, well done!

  • @boxiangwang
    @boxiangwang 4 года назад +13

    Mega BAMM!! I really love the explanation. Awesome!

  • @alinadi9427
    @alinadi9427 7 месяцев назад +1

    this playlist is excellent

  • @ayushipal7605
    @ayushipal7605 10 месяцев назад +1

    Hats off to you Josh!!
    So nicely explained ❤

    • @statquest
      @statquest  10 месяцев назад

      Glad you liked it!

  • @mohammadhaji2191
    @mohammadhaji2191 3 года назад +1

    That was the best explanation I had ever seen. Thank you very much.

  • @girmazewdie8366
    @girmazewdie8366 Год назад +1

    Thank you so much for sharing your knowledge, it is really so increadibly helped me understand the basics of the NN.

  • @KayYesYouTuber
    @KayYesYouTuber Год назад +1

    This is simply beautiful!. You are the best.

  • @石政泰
    @石政泰 4 месяца назад +1

    I am on vacation in Hawaii but I am watching your neural network video. This video is so entertaining to watch :) Tai

    • @statquest
      @statquest  4 месяца назад +1

      BAM! Have a great vacation! :)

    • @石政泰
      @石政泰 4 месяца назад +1

      @@statquest thank you! you too. have a nice day

  • @snp27182
    @snp27182 3 года назад +1

    You're a legend Doctor Starmer.

  • @mahfuzurrahmanabeed4349
    @mahfuzurrahmanabeed4349 2 месяца назад +1

    I wish I could have taken your classes when I was back in high school.

  • @amarnathmishra8697
    @amarnathmishra8697 3 года назад +1

    Well you actually make complex things super easy.Hats off and of course BAAA...M!!!

  • @abhijeetmhatre9754
    @abhijeetmhatre9754 3 года назад +1

    This is just awesome. I had started learning machine learning algorithm from multiple sources until I found your youtube channel. And now I don't have to check for any other source for understanding any ML algorithm. Looking Forward for more deep learning videos as my area of interest is deep learning. Could you help me with a good book for deep learning? And thanks for such wonderful videos.

    • @statquest
      @statquest  3 года назад

      This series ends (for now) with Convolutional Neural Networks, so just keep watching to learn about deep learning.

  • @AnBru
    @AnBru Год назад +1

    amazing video, thanks for all your hard work on this.

  • @anashaat95
    @anashaat95 2 года назад +1

    Great explanation as usual. Thank you very much.

  • @nidakhan1412
    @nidakhan1412 Год назад +1

    thank you so much sir for clearly explaining everything

  • @ilducedimas
    @ilducedimas 2 года назад +2

    God bless this Good Man.

  • @samuelpolontalo6882
    @samuelpolontalo6882 4 года назад +1

    Best channel ever

    • @statquest
      @statquest  4 года назад +1

      Wow! Thank you! :)

  • @quantummusic2322
    @quantummusic2322 2 года назад +1

    I love you Statquest

  • @jameelabot9122
    @jameelabot9122 4 месяца назад

    Love your videos man, very helpful at providing detail without sacrificing clarity. However I have noticed quite a few errors across the videos, generally small errors such as saying the wrong numbers or when calling up examples such as in this video at 9:26. input_3 would be 0, not 1. Again, it is not a major error and the information provided is nonetheless exemplary however it does make following along a tad challenging when trying to listen to the video rather than watching it like a hawk. Keep up the good work man, much appreciated x

    • @statquest
      @statquest  4 месяца назад

      I'm glad you like my videos. It is indeed unfortunate that a few of them have small "typos". However, the example you provide is not one of them. The inputs to the neural network are the x-axis coordinates, not the y-axis coordinates. The 3rd data point has an x-axis coordinate of 1 and a y-axis coordinate of 0. Thus, for the 3rd data point, the input to the neural network is 1 and the desired output is 0. So, not only is this not a major error, it's not an error at all.

  • @mikhailbaalberith
    @mikhailbaalberith 3 года назад +1

    Hey Josh, this is dope. Hope you could do some videos about the Hessian and Jacobian matrices, Thanks.

    • @statquest
      @statquest  3 года назад

      I'll keep those topics in mind.

  • @emkahuda776
    @emkahuda776 4 года назад +1

    As usual, your videos are totally awesome, I like them much and easy to understand. I wonder if you will make a video about spatial transcriptomic analysis please since you uploaded the scRNA three years ago considering the spatial analysis is now more famous?

    • @statquest
      @statquest  4 года назад +1

      I'll keep it in mind.

  • @白云开
    @白云开 3 года назад +1

    BAM! Great work!

  • @lisun7158
    @lisun7158 2 года назад +1

    [Notes]
    6:44 Notation for activation functions
    2:50 Initialize weights using standard normal distribution. Q: Why N(0,1)? -- A: Just one of many ways to initialize weights. [ref. 9:50 of ruclips.net/video/GKZoOHXGcLo/видео.html&ab_channel=StatQuestwithJoshStarmer]
    Initialize bias with 0 since bias terms frequently start from 0.
    4:33 4:48 plot SSR with respect to b3

  • @edphi
    @edphi 2 года назад +1

    Thanks. Great video again and again.

    • @statquest
      @statquest  2 года назад

      Thank you very much! :)

  • @salihylmaz4694
    @salihylmaz4694 4 года назад +2

    So underrated

    • @statquest
      @statquest  4 года назад

      Glad you think so! :)

  • @killer-whale864
    @killer-whale864 2 года назад

    i hate stats, and i hate statquest. But i keep finding myself on this channel again and again

  • @omkarghadge8432
    @omkarghadge8432 3 года назад +1

    YOU ARE THE BEST!

  • @parijatkumar6866
    @parijatkumar6866 4 года назад

    Hey Josh, great video as always!!
    Can you also please point to some source with examples (with answers) which we can practice on our own?
    I know there are tons of them on internet, but you know, your selection will be really helpful as always!!

    • @statquest
      @statquest  4 года назад +3

      I don't have anything yet, but I will create a "how to do neural networks" video soon.

  • @tinacole1450
    @tinacole1450 Год назад +1

    Hi Josh! Love the videos. Do you have any posts for building models in R/Rstudio on neural networks? Thanks,Tina

  • @gero8049
    @gero8049 3 года назад +1

    Im gonna make a AI agent that create youtube bots that promotes your channel. You really deserve all kudos.

  • @Ruhgtfo
    @Ruhgtfo 3 года назад +1

    Yeaaaa finally new episodde

  • @ertreri
    @ertreri Месяц назад +1

    superb, thanks a lot.

  • @robertdavis2855
    @robertdavis2855 2 года назад +1

    I love you man! You have a sense of humor about you that is rare in deez parts lol

  • @SM-xn9bv
    @SM-xn9bv Год назад +1

    I can not thank you enough!

  • @fndpires
    @fndpires 2 года назад +1

    THIS MAN IS AN ANGEL! :D QUADRUPLE BAM!

  • @gf1987
    @gf1987 Год назад +1

    very informative ty

  • @hamidfazli6936
    @hamidfazli6936 2 года назад +1

    You are amazing!

  • @GuidedTrading_
    @GuidedTrading_ 2 года назад

    basically, taking derivatives of losses with respect to unknown terms to find how quickly the loss is changing if we change the parameters is the essence of this whole Machine learning thing.

  • @danielo6413
    @danielo6413 2 года назад +1

    Hi Josh, great video as always. One question, if I want to speak in epoch and batch terms for this video, is it correct to say that this video shows one epoch, which includes one batch that contains all 3 data points we have (Batch Gradient Descent process)? Thanks a lot !!!

    • @statquest
      @statquest  2 года назад +1

      Yes, that is correct.

  • @soraf583
    @soraf583 4 года назад +1

    Thanks for your great video as always! I have a question though after watching this video and the other SGD video you've made in the past. When calculating the gradients for each parameter with regular gradient descent, we are plugging in all of the samples into the derivative of the loss function w.r.t the current parameter; versus we will just randomly pick one sample in the same process with SGD being used. If that's the case, then what will be the purpose of looping through all the samples (with regular GD) in a complete epoch if we are already using all the samples when calculating the gradients? Thanks in advance!

    • @statquest
      @statquest  4 года назад +2

      I'm not sure I fully understand your question. The difference between "regular" and "stochastic" gradient descent in this context has to do with the summation. In "regular", the summation goes from 1 to 'n', where 'n' is the number of samples. In "stochastic", the summation goes from 1 to m, were 'm' is < 'n' and is the number of samples randomly selected for the iteration. Does that help?

    • @soraf583
      @soraf583 4 года назад +1

      @@statquest Thank you for the quick reply! Yes that’s helpful and I think I’m understanding that part. I was mixing the concept of Gradient Descent with epoch/batch numbers, but I guess whether the GD is stochastic or not has nothing to do with the general epoch/batching concept when running a neural network, as we would still need to go over all the samples in a full epoch.

  • @cairoliu5076
    @cairoliu5076 4 года назад +1

    great content!

  • @elmoreglidingclub3030
    @elmoreglidingclub3030 4 года назад

    Great video and explanation. But I'm missing something simple. The blue and orange lines are added to render the green line, right? It appears (I'm squinting) that, after convergence, the middle dose (the 1/2 dose; actually, just to the left of it) value is 1 but the intersection of the blue and orange lines is at about -.5. Adding those together gives -1, not 1. What am I missing??

    • @statquest
      @statquest  4 года назад

      You forgot to add the bias term.

  • @Aaa-vh2lm
    @Aaa-vh2lm 4 месяца назад

    Absolutely amazing! I‘ve got a question though. How do we know if we are going the right direction when calculating the new parameter.

    • @statquest
      @statquest  4 месяца назад

      The derivative tells us what direction to change the parameter. To see more details, see: ruclips.net/video/sDv4f4s2SB8/видео.html

    • @Aaa-vh2lm
      @Aaa-vh2lm 4 месяца назад +1

      @@statquest Thank you for answering even after 2 years!
      Funnily enough, while I wrote the elaboration of my question here, I stumbled upon the answer myself.
      Thank you again for your commitment. Let me tell you, that the work you do absolutely outclasses any learning material that I have stumbled across. I will definitely check out your book! Great work!

  • @puppergump4117
    @puppergump4117 2 года назад +1

    13:35 Do you mean the derivative of observed - predicted? Wouldn't that be a derivative of a single number? Or does it always just come out to be -1?

    • @statquest
      @statquest  2 года назад +1

      To get a better understanding of how we determine this derivative, check out the StatQuest on The Chain Rule: ruclips.net/video/wl1myxrtQHQ/видео.html It will explain exactly where that -1 comes from.

    • @puppergump4117
      @puppergump4117 2 года назад +1

      @@statquest Oh the derivative of the negative intercept? ok thanks

  • @NoNonsense_01
    @NoNonsense_01 2 года назад

    I think for the sake of clarity and rigour, it should be noted that all of the differentials are partial. Otherwise, some people may wonder why implicit differentiation wasn't used in such cases where W2 was differentiated with respect to W1 or vice versa.

  • @thepodfunnel
    @thepodfunnel 3 года назад +1

    BAM! that was good!

  • @chicagogirl9862
    @chicagogirl9862 6 месяцев назад +1

    OMGGGGG, Is that you who sings at "big bang theory", S12, E24???!!!!!

  • @akaBryan
    @akaBryan 2 года назад

    Hey just a question! Around 14:00, why are you taking the derivative of SSR with respect to w_3 and w_4 rather than y_2,i and y,1_i? What is the logic between choosing taking the derivative with respect to the weight rather than the functions themselves?

    • @akaBryan
      @akaBryan 2 года назад +1

      Ah nevermind, its because you want to optimize the weights w_3 and w_4, so you just take their derivative to get step size and so forth... im so dumb haha! Im assuming that in the next part then you will optimize the weights w_1 and w_2 by also connecting them to the derivative of the loss function with respect to the weights, so itll be a huge bonkers chain rule in action

    • @statquest
      @statquest  2 года назад

      Yes! It will be totally bonkers with chain rule action. :)

  • @ianholloway9493
    @ianholloway9493 26 дней назад

    Why do you not average the derivative of the SSR (the gradient). What I mean by average is dividing the derivative of the SSR by the number of training examples. I read online that this is more common practice unless we are doing stochastic gradient descent. I was a little bit confused as this was not clarified. Thanks for the video though it really helped me understand the topic better.

    • @statquest
      @statquest  26 дней назад

      As the video shows, it works just fine without averaging the SSR. However, we have a relatively small dataset and that keeps the derivative from getting out of hand. If we had tons and tons of data, the SSR alone might lead to a massive derivative that's too big to be helpful, and averaging could help with that.

  • @sattanathasiva8080
    @sattanathasiva8080 3 года назад +1

    Many many thanks for your videos.

  • @jordiwang
    @jordiwang Год назад

    AMAZING BROOOOOOOOO

  • @84mchel
    @84mchel 3 года назад

    Dw_3 = (observed-predicted) * y1. The output is also a softplus activation. Why isn’t this derivative in the chainrule? Thank you!

    • @statquest
      @statquest  3 года назад

      We include the derivative of the SoftPlus activation function in the next video (part 2), when we optimize all of the weights and biases, including the ones to the left of the activation functions: ruclips.net/video/GKZoOHXGcLo/видео.html

  • @kousthabkundu1996
    @kousthabkundu1996 4 года назад

    Sir, one question I have. when you said we randomly select w3 and w4 from standard distrib in the first iteration, that is any values from standard distrib table or we select no's w.r.t. given dataset?

    • @statquest
      @statquest  4 года назад +1

      In this example I selected random value from a standard normal distribution. This is a normal distribution with mean = 0 and standard deviation = 1 and is completely independent of the data.

  • @willw4096
    @willw4096 Год назад

    Notes: 2:31 6:14 15:57 the "y"s are calculated based on other weights (w1 and w2)

  • @alexfeng75
    @alexfeng75 5 месяцев назад

    In "d SSR/ d Predicted", is Predicted a single value like Predictedi (with index i ) or a collection of values as i can range from 1 to 3?

    • @statquest
      @statquest  5 месяцев назад

      A collection of values. You can tell if you keep watching the video and see how it is used.

    • @alexfeng75
      @alexfeng75 5 месяцев назад +1

      @@statquest thank you for the prompt reply, Josh! you are the best!

  • @shubhamkumar-nw1ui
    @shubhamkumar-nw1ui 2 года назад +1

    My regards to the friendly folks of the genetics department of University of North Carolina at Chapel Hill

  • @_epe2590
    @_epe2590 3 года назад

    BAM!! I finally understand
    but....
    Am I correct to say that if I was optimizing 3 weights and biases at the same time i would do gradient descent in a function with 3 dimensions (1 for each weight and bias)??

  • @debadridutta
    @debadridutta 3 года назад

    The God! Please do NLP also

  • @dodosadventures7593
    @dodosadventures7593 9 месяцев назад

    Hi Josh ! Love your videos, could you please explain why normal distribution is used to initialise w3 and w4 or else if you have already uploaded a video on normal distribution can you tag it

    • @statquest
      @statquest  9 месяцев назад

      It's just a standard way to do it. However, you can use uniform distributions or other distributions if you would like. One thing people like about the normal distribution is that changing the standard deviation for each hidden layer can make it easier to train deeper models (models with lots of hidden layers).

  • @madghostek3026
    @madghostek3026 Год назад

    Small question: since we fiddle with all (or part) of the parameters at once, and for example bias is dependent on weights on the graph, does that mean they fight with each other? Can something be done about it? Like we calculate the derivatives for current forward pass, ok, but then changing all parameters at once to what the think is optimal might throw off everything, since they can't communicate in any way, how does it not explode?

    • @statquest
      @statquest  Год назад

      In my video on gradient descent, I show how to optimize two parameters at the same here: ruclips.net/video/sDv4f4s2SB8/видео.html In that video, we're trying to fit a straight line to some data points and are using gradient descent to find the best values for two parameters, the y-axis intercept and the slope. If you watch, you'll see a fancy graph, where one axis represents different values for the y-axis intercept and another axis represents different values for the slope. When we optimize both at the same time, we take a step towards a better intercept on that axis and take a step towards a better slope on that axis, which is different, and doesn't affect the one the intercept is on. So the parameters don't fight each other because each one gets its own axis to work on. That being said, we can still get stuck in a local minimum, but it's like progress in one parameter can be negated by progress in another.

    • @madghostek3026
      @madghostek3026 Год назад +1

      @@statquest Ah, this makes a lot of sense now, I think I know why it was misleading for me - in the end all you see a numerical value, the error, but behind the scenes the partial derivatives take apart the loss function in their own domains, so it's not just one number. Thank you for very descriptive response!

    • @statquest
      @statquest  Год назад

      @@madghostek3026 bam! Your question is actually a very good one and maybe one day I'll make a short video that explains it for everyone.

  • @roberthuff3122
    @roberthuff3122 5 месяцев назад +1

    The nested chain rule.

  • @creativeo91
    @creativeo91 4 года назад +1

    Please make a tutorial on Gaussian mixture model and EM algorithm

    • @statquest
      @statquest  4 года назад +1

      I'll keep that in mind.

    • @creativeo91
      @creativeo91 4 года назад +1

      @@statquest thanks..
      It will be really helpful 🙂

  • @akshaynn4651
    @akshaynn4651 2 года назад

    when i plug the value -1.43 into the equation log(1 + e**x) i get 0.093. should I use the base 10 for log or a different one?

    • @statquest
      @statquest  2 года назад

      In statistics, data science, machine learning and almost all programming languages, the default base for the log function is 'e', and that's what I use here.

    • @akshaynn4651
      @akshaynn4651 2 года назад +1

      @@statquest Thanks, this was very helpful.

  • @kiranchowdary8100
    @kiranchowdary8100 4 года назад +2

    i dont know how u feel but i feel very bad that your are not recognized as much as you should be (from india )

    • @statquest
      @statquest  4 года назад +1

      Thanks!

    • @kiranchowdary8100
      @kiranchowdary8100 4 года назад +2

      @@statquest urs is the first channel I purchased member ship and God I am the most conjuze(resistant. In spending money)person I ever saw

    • @statquest
      @statquest  4 года назад +1

      @@kiranchowdary8100 WOW! That is awesome!!! Thank you so much for your support. It means a lot to me that you care enough to contribute.

  • @karrde666666
    @karrde666666 3 года назад +1

    The right way to learn, textbooks and lectures should be obsolete

  • @dahirou_harden
    @dahirou_harden 5 месяцев назад

    Just wanted to clarify. Is the output given at the end of each pass an actual function or just a set of 3 points (summed from y1 and y2)? Thanks!

    • @statquest
      @statquest  5 месяцев назад

      What time point, minutes and seconds, are you asking about?

    • @dahirou_harden
      @dahirou_harden 5 месяцев назад

      @@statquest Basically I'm just confused about if the final curve approximating the 3 points is a "curve" as in a polynomial, or just a set of 3 points. Because when we add the two activation functions, you talked about adding them at each point as if we were adding the equations for the lines themselves, in order to get the final line. But it seems like instead we're just adding the y values at each input (the 3 given inputs) rather than a line itself..?

    • @dahirou_harden
      @dahirou_harden 5 месяцев назад

      @@statquest At 4:03 for example.

    • @statquest
      @statquest  5 месяцев назад +1

      @@dahirou_harden The adding is done for all possible x-axis coordinates (or input values), and thus, we are adding the lines themselves, not just the 3 points. The points (or circles) on the lines are just to illustrate the concept of adding y-axis values, and do not to limit the adding to just those points.

  • @giorgosmaragkopoulos9110
    @giorgosmaragkopoulos9110 8 месяцев назад

    So what is the clever part of back prop? Why does it have a special name and it isn't just called "gradient estimation"? How does it save time? It looks like it just calculates all derivatives one by one

    • @statquest
      @statquest  8 месяцев назад

      Backpropagation refers to how the gradient is calculated. Gradient Descent is how the gradient is used.

  • @macknightxu2199
    @macknightxu2199 Год назад

    Hi, how to understand back? not forward or other direction? I mean the video is nice, but didn't explain to clear why backward is important. Why not forward?

    • @macknightxu2199
      @macknightxu2199 Год назад +1

      got it. At the back point, the derivative is much simpler than the derivatives at the front. So, as we would like to go from simple to hard, we'd choose from back to front. That's why it's backpropagation, which is discussed in the next video.
      BR

    • @statquest
      @statquest  Год назад +1

      bam! :)

  • @zer995
    @zer995 3 года назад +1

    Triple BAM!!! That's what I said when I knew my girl, married her and got children :)