Backpropagation explained | Part 1 - The intuition

  Рет қаралды 117,456

deeplizard

deeplizard

Күн бұрын

Пікірлер: 125
@danluba
@danluba 6 жыл бұрын
This video deserves to be on television at dinner time.
@parthasarathybalaraman1800
@parthasarathybalaraman1800 6 жыл бұрын
I have just completed watching all the 27 videos in the list. All are excellent videos!! Thanks for uploading. Please continue the good work!! Thanks!
@deeplizard
@deeplizard 6 жыл бұрын
Hey Parthasarathy - That's great to hear that you've gone through the entire playlist! I'm glad you're enjoying them!
@maedehzarvandi3773
@maedehzarvandi3773 4 жыл бұрын
your videos are actually great in expressing the concepts in possibly quickest time . i havnt seen your other playlists yet. but this one really helped me so much.
@husseinwassouf2743
@husseinwassouf2743 4 жыл бұрын
this course is so nice you are simplifying complex ideas in a really nice way, I think this series should be binge watched like a netflix series to refresh your memory on all these concepts XD
@justchill99902
@justchill99902 6 жыл бұрын
There is no limit to the awesomeness of her explanation!
@luna-kr3zc
@luna-kr3zc 5 жыл бұрын
there's a whole team behind this she is just the voice (but she does a great job at it)
@deeplizard
@deeplizard 6 жыл бұрын
Backpropagation explained | Part 1 - The intuition kzbin.info/www/bejne/jnaWnKWcaKiEotU Backpropagation explained | Part 2 - The mathematical notation kzbin.info/www/bejne/aJ62qqaIrZJkmZI Backpropagation explained | Part 3 - Mathematical observations kzbin.info/www/bejne/fWbFZZ2Id7CBrtk Backpropagation explained | Part 4 - Calculating the gradient kzbin.info/www/bejne/kKOYp5x3j6yhmqc Backpropagation explained | Part 5 - What puts the “back” in backprop? kzbin.info/www/bejne/rnTPfJKVeNaNpLM Note, at 7:44, I misspoke when I stated that the updated values we get for the weights are the the corresponding derivatives of the loss function with respect to each weight. Actually, the updated values themselves are *not* the derivatives. Rather, after calculating the derivatives, the weights are updated to their new values, which are calculated *using* the derivatives we obtain. This process of updating the weights is covered in more detail in the following video. This particular detail is mentioned at 1:26: kzbin.info/www/bejne/lX-YnKOJgqmZatEm26s Machine Learning / Deep Learning Fundamentals playlist: kzbin.info/aero/PLZbbT5o_s2xq7LwI2y8_QtvuXZedL6tQU Keras Machine Learning / Deep Learning Tutorial playlist: kzbin.info/aero/PLZbbT5o_s2xrwRnXk_yCPtnqqo4_u2YGL
@GirlKnowsTech
@GirlKnowsTech 3 жыл бұрын
00:00 Intro 01:23 Recap stochastic gradient descent (SGD) 04:42 What is backpropagation, the intuition 08:28 Summary
@deeplizard
@deeplizard 3 жыл бұрын
Added to the description. Thanks so much!
@RaghavendraBoralli
@RaghavendraBoralli 6 жыл бұрын
Yes i want to know on the math behind backprop
@kareemjeiroudi1964
@kareemjeiroudi1964 6 жыл бұрын
Me too!
@piyushchauhan343
@piyushchauhan343 4 жыл бұрын
Jan ke kia karo ge
@zw9423
@zw9423 5 жыл бұрын
Omg Thank You! All these books make it so complex and include a bunch of unnecessary equations before a noob like me can actually understand the process. I am interested in the math as well but first I have to know the concept, otherwise I often find myself understanding these complex details and be like, why exactly are we doing this? This video actually makes sense and now I can dive deeper into it. Nice animations too. Props to you guys
@deeplizard
@deeplizard 5 жыл бұрын
You're welcome, Zi! Glad you found it helpful. The math explanations are in the following videos of this playlist.
@hkrishnan91
@hkrishnan91 3 жыл бұрын
Bless you for making the world a better place. Keep up the good work!
@ThePRINCEBARPAGA
@ThePRINCEBARPAGA 5 жыл бұрын
I cannot thank you enough. I don't know how many videos I watched to clear this concept, nothing helped but your video. You explained it in a very detailed and clear way. Thank You so much!
@nicholasscotto3712
@nicholasscotto3712 2 жыл бұрын
after watching sooooooo many videos on this topic yours was EASILY the most helpful by far. It is accurate, simple, and just all around perfect. the image is very simple. I love your voice and the explanation is so good.
@RohanPaul-AI
@RohanPaul-AI 3 жыл бұрын
Just can not THANK YOU enough for this Greatest of videos on the topic. Just Brilliant.
@tymothylim6550
@tymothylim6550 3 жыл бұрын
Thank you very much for this video! It was fantastic that I could finally understand how SGD uses back propagation to calculate the gradients to minus off!
@ismailelabbassi7150
@ismailelabbassi7150 3 жыл бұрын
YES YES YES YES YES YES WE NEED MATH TOPICS
@mohamedmahdy969
@mohamedmahdy969 6 жыл бұрын
I already know the math behind back propagation; however, I will watch your videos in order to see how you are going to present it. Your way of giving the information is awesome. I want to see how it will work with the math complexity.
@deeplizard
@deeplizard 6 жыл бұрын
Thanks, Mohamed! Let me know your thoughts after you finish the following math videos.
@mohamedmahdy969
@mohamedmahdy969 6 жыл бұрын
@@deeplizard To be honest, as I mentioned earlier, I already know the math behind the back propagation, yet your videos were a good refresh to me. You used the same mathematical notation and the same methodology of my teacher. he started with the last hidden layer; after that, he generalized to any hidden layer. Thanks a lot for your videos.I already finished the math videos and I will finish this list today. In the future, I am going to watch tensorFlow.js series
@deeplizard
@deeplizard 6 жыл бұрын
Great to hear, Mohamed! Thanks for letting me know. Would love to hear how your progression is going in the TensorFlow.js series as well once you start!
@yzyangliang
@yzyangliang 5 жыл бұрын
This is an amazing video and I understand the deep learning instantly!
@cedricrogers8102
@cedricrogers8102 6 жыл бұрын
This was a very clear explanation of what happens during back propagation. The next step is to provide the math. Thank you for your effort. Great Job.
@deeplizard
@deeplizard 6 жыл бұрын
Thanks, cedric! The full math for backprop is covered in the videos following this one! :) They are currently #28 - 31 in this playlist: kzbin.info/aero/PLZbbT5o_s2xq7LwI2y8_QtvuXZedL6tQU
@cedricrogers8102
@cedricrogers8102 6 жыл бұрын
deeplizard I will watch them thanks again
@deepaksingh9318
@deepaksingh9318 6 жыл бұрын
Yess.. Adding a specific Playlist with Maths behind all the functionality with an example (Like uh showed for max pooling which was visible to see hoe things are working with input) would be really great.. Bur still appreciate your efforts in helping students by such a great videos..
@deeplizard
@deeplizard 6 жыл бұрын
Thanks, deepak. The next four videos in this playlist show the full math behind backpropagation. Let me know how it goes as you progress through them!
@qusayhamad7243
@qusayhamad7243 4 жыл бұрын
thank you very much for this clear and helpful explanation. Words fail to express my gratitude.
@javierCi
@javierCi 6 жыл бұрын
Thanks you very much for making this great videos. And I want to know more about maths
@paragjp
@paragjp 4 жыл бұрын
Hi, Thanks for super clean way to explaining basic concepts. Keep it up. Request you for following video series 1. Complete Maths and Stats for ML/Deep Learning. 2. Pl have additional series on calculus on backpropogation. 3. Make complete new series on ML/Deep Learning Practical projects rather than Housing Price Prediction, Titanic, iris, Hand written digits ....etc
@MsStoCa
@MsStoCa 4 жыл бұрын
Hey! What's going on everyone? :D Great content!
@TheMeltone1
@TheMeltone1 2 жыл бұрын
You are truly a fantastic teacher :)
@rajuthapa9005
@rajuthapa9005 6 жыл бұрын
yes math too please.
@DM-py7pj
@DM-py7pj Жыл бұрын
These are excellent videos. I do worry about biases not being discussed in later videos as these are also being updated.
@dan7582
@dan7582 2 жыл бұрын
At 8:00 you say that the update values of the weights are equal to their derivatives (gradient). But since we are talking about a loss function, they should be equal to de NEGATIVE gradient instead?
@flamboyanz
@flamboyanz 6 жыл бұрын
Thank you so much for this! Its concise and well explained.
@deeplizard
@deeplizard 6 жыл бұрын
You're very welcome, Parvez!
@travel7517
@travel7517 6 жыл бұрын
great..explaination...simple and effective
@robertoooooooooo
@robertoooooooooo 6 жыл бұрын
Amazing, love your videos, will recommend it to all my friends
@deeplizard
@deeplizard 6 жыл бұрын
Thank you, Robert!
@faraazmohammed3693
@faraazmohammed3693 6 жыл бұрын
please make a series on videos explaining math behind machine learning and deep learning in particular. Thanks for Amazing videos.
@deeplizard
@deeplizard 6 жыл бұрын
Hey Faraaz - You're welcome! Did you see the next four videos in the playlist that cover the full math for backprop?
@richarda1630
@richarda1630 3 жыл бұрын
such an awesome super simple explanation! and how you bring up the math, it's almost like a teaser :) now I want to see the Math! =)
@1sankey2
@1sankey2 4 жыл бұрын
Great video I wanna see the math. Thank you for uploading this one.
@deeplizard
@deeplizard 4 жыл бұрын
Great :D It's in the following episodes. Starting with this one: deeplizard.com/learn/video/2mSysRx-1c0
@Arcaerus
@Arcaerus 2 жыл бұрын
I would greatly appreciate if you could make a series on how to take the derivative of a bunch of layers! Thank you for these videos!
@samaryadav7208
@samaryadav7208 6 жыл бұрын
Wow that was exciting Hi. Thanks for sharing these videos. And Also we want to see the maths.
@fahimmahmud3115
@fahimmahmud3115 4 жыл бұрын
{ "question": "Since the derivative of the loss function is calculated with respect to the weights of the model during backpropagation, what characteristics should the loss function have?", "choices": [ "Continuous", "Discontinuous", "Constant", "Zero" ], "answer": "Continuous", "creator": "Fahim Mahmud", "creationDate": "2020-02-12T04:10:35.701Z" }
@deeplizard
@deeplizard 4 жыл бұрын
Thanks, Fahim! Just added your question to deeplizard.com/learn/video/XE3krf3CQls :)
@mjain2172
@mjain2172 4 жыл бұрын
Yes, please explain math behind of this calculation, thanks for explaining deep neural network concepts
@deeplizard
@deeplizard 4 жыл бұрын
Great :D The math is included in the following episodes. Starting with this one: deeplizard.com/learn/video/2mSysRx-1c0
@krishnasaibiradar
@krishnasaibiradar 4 жыл бұрын
Thanks for the awesome video on backpropagation Yes i want to know the math behind backpropagation as the whole logic lies in and around math.So kindly make a video on the math behind the Backpropagation.
@deeplizard
@deeplizard 4 жыл бұрын
You're welcome, krishnasai! There are 4 episodes following this one that explain the math :) And they all have corresponding blog articles along with the video! The next one starts at the link below, and the following 3 are directly after. deeplizard.com/learn/video/2mSysRx-1c0
@loganmay2105
@loganmay2105 4 жыл бұрын
Never thought I'd hear the words "chain rule" outside of my old high school AP calc class
@deeplizard
@deeplizard 4 жыл бұрын
🤓
@krishnaik06
@krishnaik06 6 жыл бұрын
Math too please
@avibcci1297
@avibcci1297 8 ай бұрын
interesting
@omargonalfa
@omargonalfa 5 жыл бұрын
Awesome video. please a brief example of the math behind.
@deeplizard
@deeplizard 5 жыл бұрын
The math is shown in the following four videos of the series :D
@fritz-c
@fritz-c 4 жыл бұрын
I noticed a broken link in the article for this video, near the words: "shown in an [earlier post]." It looks like part of the url got duplicated.
@deeplizard
@deeplizard 4 жыл бұрын
Fixed, thanks Chris! :D
@nourelislam8565
@nourelislam8565 2 жыл бұрын
Amazing... Before asking about the math courses for the backpropagation. Is it essential to study the math behind deep learning in order to work with Keras or any other APIs? Thanks for these fruitful videos!
@generalzeedot
@generalzeedot 4 жыл бұрын
would this backpropagation technique, therefore, only be usable in supervised learning?
@jesilmohammed7926
@jesilmohammed7926 5 жыл бұрын
What is the default height and width of a conv_2d filter ?
@vantongerent
@vantongerent 3 жыл бұрын
great video - yes I want to see the math! 🙂
@richardme9928
@richardme9928 5 жыл бұрын
Any links to videos that do the complete math calculations ?
@deeplizard
@deeplizard 5 жыл бұрын
Hey richard - They are the following videos in this playlist. Check out the full series in order here: deeplizard.com/learn/playlist/PLZbbT5o_s2xq7LwI2y8_QtvuXZedL6tQU
@sanketkachole9639
@sanketkachole9639 2 жыл бұрын
yes we need it
@deeplizard
@deeplizard 2 жыл бұрын
You got it - Math starts in the next episode :D kzbin.info/www/bejne/aJ62qqaIrZJkmZI
@VISWESWARAN1998
@VISWESWARAN1998 5 жыл бұрын
Thank you so much
@GelsYT
@GelsYT 4 жыл бұрын
Hello :D Is the output of the activation equal to the weight ? i mean is the activation the weight? of every neuron firing? right? cause i think that's what I remember about your video on activation function so basically the output of the activation function is going to be the weight? thank you so much great tutorial ! you explain it at the simplest way :))
@rohtashbeniwal9202
@rohtashbeniwal9202 4 жыл бұрын
great videos,,saveed,subscribed ,
@deeplizard
@deeplizard 4 жыл бұрын
Awesome, thank you!
@jabrams3643
@jabrams3643 6 жыл бұрын
i'm confused about the difference between the gradient and derivative? Is it called a gradient of the loss function when you average out all of the derivatives of the loss wrt to a certain weight? Meaning that its called a derivative when its just dloss/dweight for a single sample, and its called a gradient when its the average dloss/dweight for all of the samples? thank you for this amazing series btw it is the best on the internet
@GelsYT
@GelsYT 4 жыл бұрын
sooo gradient descent is the one who's updating the weights? thank you soo much
@deeplizard
@deeplizard 4 жыл бұрын
Yes it is!
@abail7010
@abail7010 5 жыл бұрын
Something isn't clear tome. Do we update the bias for each neuron or is this example without using bias? Apart from that, I love your videos and the way you explain things! Please keep up since this is a highly interesting thing. :)
@deeplizard
@deeplizard 5 жыл бұрын
Thank you, Xi! I've left bias out of this example, but they get updated at the same time and in the same fashion as the weights.
@abail7010
@abail7010 5 жыл бұрын
Thank you for the reply! I've not seen your video to the bias which cleared my question when I commented. :)
@herohari27
@herohari27 6 жыл бұрын
In which video you were talking about SGD?
@deeplizard
@deeplizard 6 жыл бұрын
Hey Hari - These two: deeplizard.com/learn/video/sZAlS3_dnk0 deeplizard.com/learn/video/_N5kpSMDf4o
@zrmsraggot
@zrmsraggot 5 жыл бұрын
Why cant we just change the weights from pink to blue nodes since we just want activation in blue nodes to change to be efficient
@ojasvinnagpal9472
@ojasvinnagpal9472 4 жыл бұрын
I have a similar question: Why can't we simply change the weights between the blue and the yellow nodes and arrive at the optimal values for the hidden layer units?
@ojasvinnagpal9472
@ojasvinnagpal9472 4 жыл бұрын
Is it the case that in order to change the nodes in each layer, we need to change BOTH the nodes in the previous layer as well as the weights between the previous layer and the current layer?
@meetayan15
@meetayan15 6 жыл бұрын
hi, do you have any lecture on SGD ?
@deeplizard
@deeplizard 6 жыл бұрын
Hey Ayan - The following two videos (in the order listed) talk about SGD: 1. kzbin.info/www/bejne/qYuknYZplMmhoZI 2. kzbin.info/www/bejne/lX-YnKOJgqmZatE Note that SGD uses backpropagation during training, which is where most of the "grunt work" comes into play. So after generally understanding what SGD is doing from the above videos, this 5-part backprop series, starting with the video we're currently commenting on, gives all the details for what backprop is doing during the training process.
@xeroxSoldier
@xeroxSoldier 5 жыл бұрын
Love your videos, really helping me with my master thesis! :) You're talking about SGD but there are also other optimizers. I'm interested especially in Adam, and how it differs from SGD, maybe you got some paper or article recommondations? - In my understanding Adam is doing the exact same thing as SGD just using another algorithm, is that correct? - You're talking about backpropagation referring to SGD, is Adam also using backpropagation? In my understanding, backpropagation ist just the general term of changing the weights after every forward propagation.
@torbjornstorli2880
@torbjornstorli2880 6 жыл бұрын
Is the backpropagation being applied only once per epoch? So, if you have 20 epochs you will perform backpropagation 20 times, once per epoch ?
@deeplizard
@deeplizard 6 жыл бұрын
Hey Torbjorn - It occurs at each batch. The details for this implementation are covered in the backprop videos that come after this one in the playlist.
@stydras3380
@stydras3380 4 жыл бұрын
I can only agree with the other comments, knowing the math is neat :D Is there some sort of follow up video of yours?
@stydras3380
@stydras3380 4 жыл бұрын
Ok, I have found the videos discussing the math :D
@rajuthapa9005
@rajuthapa9005 6 жыл бұрын
r u bringing RNN tut too?
@deeplizard
@deeplizard 6 жыл бұрын
Hey Raju - Yes, I have RNNs on my list to cover in future videos.
@aamir122a
@aamir122a 6 жыл бұрын
same here.
@sprajapati2011
@sprajapati2011 4 жыл бұрын
7:17 'ie' is pronounced as 'that is' not i e itself
@aliasgarzakir4779
@aliasgarzakir4779 5 жыл бұрын
Yes please, math is fun.
@deeplizard
@deeplizard 5 жыл бұрын
All the math is in the episodes following this one :D
@torbjornstorli2880
@torbjornstorli2880 6 жыл бұрын
That is per batch per epoch
@ahdm1319
@ahdm1319 5 жыл бұрын
please explain the maths behind this in seperate videos
@deeplizard
@deeplizard 5 жыл бұрын
The math is shown in the next four videos after this one. Let me know what you think!
@saranshtayal2526
@saranshtayal2526 4 жыл бұрын
i want to know about the math
@deeplizard
@deeplizard 4 жыл бұрын
It's in the following episodes after this one :)
@danluba
@danluba 6 жыл бұрын
And yes, I could go for some math.
@deeplizard
@deeplizard 6 жыл бұрын
The math for backprop starts in the next video in the playlist! Here are the full details for the backprop series: Backpropagation explained | Part 1 - The intuition (this video) kzbin.info/www/bejne/jnaWnKWcaKiEotU Backpropagation explained | Part 2 - The mathematical notation kzbin.info/www/bejne/aJ62qqaIrZJkmZI Backpropagation explained | Part 3 - Mathematical observations kzbin.info/www/bejne/fWbFZZ2Id7CBrtk Backpropagation explained | Part 4 - Calculating the gradient kzbin.info/www/bejne/kKOYp5x3j6yhmqc Backpropagation explained | Part 5 - What puts the “back” in backprop? kzbin.info/www/bejne/rnTPfJKVeNaNpLM
@danluba
@danluba 6 жыл бұрын
Yeah - I found it. Awesome stuff. Thank you!
@deeplizard
@deeplizard 6 жыл бұрын
Awesome, you're welcome!
@josegregorioperezmagallane3211
@josegregorioperezmagallane3211 5 жыл бұрын
We want to Sep the math
@deeplizard
@deeplizard 5 жыл бұрын
The math explanation is in the following four videos of the series :D
@urvashidang6083
@urvashidang6083 4 жыл бұрын
i want to know the maths behind
@deeplizard
@deeplizard 4 жыл бұрын
Great! It's in the following episodes. Starting with this one: deeplizard.com/learn/video/2mSysRx-1c0
@wesleyrademaker5167
@wesleyrademaker5167 5 жыл бұрын
math please!
@deeplizard
@deeplizard 5 жыл бұрын
Hey Wesley - The math is in the following four videos after this one in the playlist!
@yvesa6959
@yvesa6959 3 жыл бұрын
give maths pls
@deeplizard
@deeplizard 3 жыл бұрын
The math comes in the episodes that follow this one :D
@MrFranciscoooooo
@MrFranciscoooooo 4 жыл бұрын
A video for this a video for that!! Just teach or do a brief sum of what this is, because if I want to search more I will do it from other videos not just yours.
@lando6583
@lando6583 6 жыл бұрын
i don't want to know about the math.
@deeplizard
@deeplizard 6 жыл бұрын
Warning: Don't watch parts 2 - 5 of the backprop videos 😜
@akshatsahu2637
@akshatsahu2637 5 жыл бұрын
The background is so bad. The image and background blend
@deeplizard
@deeplizard 5 жыл бұрын
I agree the image and the background don't have enough contrast with each other. The background has changed in later videos.
@akshatsahu2637
@akshatsahu2637 5 жыл бұрын
@@deeplizard rest all the videos are very very good. The way everything is explained is awesome!. Better that course era. One last things, are there any videos in which the programming part is explained or the dimensions of the error or Delta, and the dimensions of theta?
@jesilmohammed7926
@jesilmohammed7926 5 жыл бұрын
What is the default height and width of a conv_2d filter ?
Backpropagation explained | Part 2 - The mathematical notation
11:03
Support each other🤝
00:31
ISSEI / いっせい
Рет қаралды 81 МЛН
Леон киллер и Оля Полякова 😹
00:42
Канал Смеха
Рет қаралды 4,7 МЛН
How a Neural Network Learns explained
7:00
deeplizard
Рет қаралды 113 М.
Batch Normalization (“batch norm”) explained
7:32
deeplizard
Рет қаралды 233 М.
Backpropagation, step-by-step | DL3
12:47
3Blue1Brown
Рет қаралды 4,8 МЛН
But what is a neural network? | Deep learning chapter 1
18:40
3Blue1Brown
Рет қаралды 18 МЛН
Gradient descent, how neural networks learn | DL2
20:33
3Blue1Brown
Рет қаралды 7 МЛН
Learnable Parameters in an Artificial Neural Network explained
6:34
Max Pooling in Convolutional Neural Networks explained
10:50
deeplizard
Рет қаралды 159 М.
Regularization in a Neural Network explained
5:55
deeplizard
Рет қаралды 88 М.
Support each other🤝
00:31
ISSEI / いっせい
Рет қаралды 81 МЛН