Tutorial 6-Chain Rule of Differentiation with BackPropagation
Vložit
- čas přidán 18. 07. 2019
- In this video we will discuss about the chain rule of differentiation which is the basic building block in BackPropagation.
Below are the various playlist created on ML,Data Science and Deep Learning. Please subscribe and support the channel. Happy Learning!
Complete Deep Learning: • Tutorial 1- Introducti...
Data Science Projects playlist: • Generative Adversarial...
NLP playlist: • Natural Language Proce...
Statistics Playlist: • Population vs Sample i...
Feature Engineering playlist: • Feature Engineering in...
Computer Vision playlist: • OpenCV Installation | ...
Data Science Interview Question playlist: • Complete Life Cycle of...
You can buy my book on Finance with Machine Learning and Deep Learning from the below url
amazon url: www.amazon.in/Hands-Python-Fi...
🙏🙏🙏🙏🙏🙏🙏🙏
YOU JUST NEED TO DO
3 MAGICAL THINGS
LIKE
SHARE
&
SUBSCRIBE
TO MY CZcams CHANNEL
📚📚📚📚📚📚📚📚
Hello Sir, I think there is mistake in this video for backpropagation. Basically to find out (del L)/(del (w11^2)), we don't need the PLUS part. Since here O22 doesn't depend on w11^2. Please look into that. The PLUS part will be needed while calculating (del L)/(del (w11^1)), there O21 & O22 both depend on O11 and O11 depends on w11^1.
Yes brother there is mistake what is said is correct
Yes, This is correct. Thank you for pointing this out.
true that
You are correct concerning that, but I think he wanted to take derivative w.r.t O11 since it is present in both nodes of f21 and f22, so if we replace w11^2 in the equation by O11 the equation would be correct
it took me time to understand it but now I got the point thanks man but I can assure you that @krish naik is the first professor I have
you are no one but the perfect teacher,keep on adding playlist
I don't want to calulate Loss function to your videos and no need to propagate the video back and forward i.e you explained in such a easiest way I have ever seen in others. Keep doing more and looking forward to learn more from you. Thanks a ton.
This is simply yet Superbly explained. When I learnt earlier, it stopped at Back Propagation. Now, learnt what is in Backpropagation that makes the Weights updation in an appropriate way, i.e., Chain rule. Thanks much for giving clarity that is easy to understand. Superb.
This video explained everything I needed to know about backpropagation. Great video sir.
Your videos are really helping me to learn Machine learning as an actuarial student who is from a pure commerce/ finance background
Deep Learning Playlist concepts are very clear and anyone can understand easily. Really have to appreciate your efforts 👏🙏
This is the most clear mathematical explanation I have ever seen till now.
czcams.com/video/Ixl3nykKG9M/video.html
Jabardast sir, i am watching ur videos after watching Andrew Ng's lecture of deep learning. I will say you simply explained even more easily. Superb.
Yes man, he's very good.
one of the best videos, I have seen in my life!!
simply one word "Great"
Well Explained sir ! Before starting the deep learning, I have decided to start the learning from your videos. You explain in very simple way ...Anyone can understand from your video. Keep it up Sir :)
Of the two connections from f11 to the second hidden layer, w11^2 is affecting only f21 and not f22(as it affected by w21^2). So, dL/dw11^2 will only have one term instead of two.
Anyone, pls correct me if i am wrong.
I agree. i dont know why others didn't realized this same mistake!!!
i agree, i was looking for someone has the same remark :)
That's the point I am actually looking
Exactly, cause if I solve the derivative of two terms it results d/dw11^2 *L = d/dw11^2 *L + d/dw12^2 *L , which is wrong
Absolutely.
It has been years since I had solved any mathematics question paper or looked at mathematics book. But the way you explained was damn good than Ph.D. holder professors at the University. I did not feel my away from mathematics at all. LoL- I do not understand my professors but understand you perfectly
Thank you for the perfect DL Playlist to learn, wanted to highlight a change to make it 100% useful (Already at 99.99%),
13:04 - For Every Epoch, the Loss Decreases adjusting according to the Global Minima.
But for negative slopes loss has to increase know to reach global maxima
You have explained it very well. Thanks a lot!
Thank you so much for all your efforts to give such an easy explanation🙏
great video especially you are giving the concept behind it, love it.. thank you for sharing with us.
Really appreciable the way you taught Chain rule...awesome..
Great explanation. I was looking for this clarity since long...
clearly understood very much appreciated for your effort :)
You have saved my life, i owe you everything
Amazing Videos...Only one word to say "Fan"
This is really cool. First time samjh aaya. Hats off Man.
OP... Nice Teaching... Why don't we get teachers like u in every institute and college??
Thank you so much for this! You are a good teacher
hats off to you sir,Your explanation is top level, THnak you so much for guiding us...
Thanks ! That was really awesome.
first time i undestand very well by your explanation.
Just awsome explanation of gradient descent.
Excellent presentation Krish Sir .. You are great
Brilliant explanation!
Krish your awesome finally I understood the chain rule from you thanks Krish again
Great stuff for free. Kudos to you and your channel
Great way to explain man.... keep on going
thank you sir, you explain very good keep it up.
love you sir, love ur effort. love from Bangladesh.
Nice informative video. It helped me in understanding the concept. But i think at end there is a mistake. You should not add the other path to calculate the derivative for W11^2. Addition should be done if we are calculating the derivative for O11.
w11^2(new) = (dl/dO31 * dO31/dO21 * dO21/dW11^2)
Yes deepak, I noticed the same thing. There's a mistake around 12:21. no addition is needed.
yes deepak you are correct. I also think the same.
Is that because we are calculating based on o3 and 03 depends on both output from second layer
great effort...
so helpful video :)
thanks
Thanks a lot for the videos it helped me a lot
You are too Good Krish , nice Data science content
Very very good explanation..very much understandable. Can I know how many days ur planning to complete this entire playlist?
Nice one thnks a lot!
❤. God bless you, Sir.
the last partial derivative of Loss we have calculated w.r.t. (w11^2) is that correct how we have shown there that it is dependent upon two paths one w11^2 and other w12^2 ......... Please make it clear i am confused about it ??????
I think this is wrong! Maybe he wanted to discuss about the w11^1? However, a forth term should be add in the sum. Idk
@@wakeupps yes, i think he got confused and it was w11^1
assume he is explaining about W11^1 and youll understand everything. From the diagram itself, you can see the connections and can clearly imagine which weights are dependent on each other .
Hope this helps
Yes, he should not have added the second term in the summation.
@@akrsrivastava Correct no second term needed for W11^2
I am going through tour videos. You are Rocking Bro.
Your*
Thanks Krish...
Nice and requested to please add some videos on optimizer...
Bro, there is a correction needed in this video... watch out for last 3 mins and correct the mistake. Thanks for your efforts
your right
Thank you sir.
Thank you Sir 🙏🙏🙏🙏♥️☺️♥️
so insightful @krish
Your teaching is great sir. But can we get some video also about how we will apply these practically in python?
Well explained video
Loved it man... Great effort in explaining the maths behind it and chain rule. Pls make a video on its implementation soon. as usual great work.. Looking forward for the videos. Cheers
Hello Sunny, I myself have stitched an absolutely brilliant repository explaining all the implementation details behind an ANN. See this: github.com/jalotra/Neural_Network_From_Scratch
@@shivamjalotra7919 Great effort. Starred it. ⭐👍🏼
@@kshitijzutshi try to implement it yourself from scratch. See george hotz twitch stream for this.
@@shivamjalotra7919 Any recommendation for understanding image segmentation problem using CNN? resources?
Excellent video, I'm new in the field, could someone explain me how the O's are obtained. Are that O's the result of each neuron computation? are the O's numbers equations?
very good content
excellent Krish
@ 10:28 - 11:22 krish do we need both the paths to get added . since w11 suffix 2 is not affected by lower path ie w12 suffix 2? please tell
The second part of the summation should not come in the picture as it will come only when we will be calculating (dL/dw12) with suffix as 2.
@@amit_sinha i think that is correct.
@@amit_sinha
Yes I have the same doubt!
Not required, its not correct as w11^2 is not affected by lower weights. The 1st part is correct and summation is required , when we are thinking about w11^1.
@@vishaldas6346 Yes!
Thank you so much for all your videos. I have a question respect of the value to assign to bias. This value is a random value? I will appreciate your answer.
thank you ser
sir i think one thing you are doing is worng.
as w^(3)11 impacts O(31) , here is one activation part.
so the dL/dw^(3)11 = dL/dO(31) . d0(31)/df1 . df1/dw^(3)11
I might be wrong, can you please clear my query ?
Can you please do a Live Q&A session !? Great video... Thank you
Let me upload some more videos, then I will do a Live Q&A session.
in the back propagation, calculation of gradients using the chain rule for the w11^1, i think we need to consider 6 paths. please kindly clarify.
Nice 👍👏🥰
Im able to understand the concepts you are explaining, but I dont know that from where do we get values for weights in forward propgation.Could you brief about that once if possible.
Sir , If to every single neuron in hidden layer we are giving same weights and features with bias then what is the use of multiple neurons in single layer?
Hi Krish,
Please upload videos on regular basis. I'm eagerly waiting for your videos.
Thanks in Advance
Uploaded please check the tutorial 7
@@krishnaik06 thank you..please keep posting more videos..I'm really waiting to watch your videos..really liked your way of explanation
finally i understand it
thanks sir
Pls upload ROC auc related concepts
Awesome Mate. however, I think you got carried away for the second part to be added. read the comments below and correct, please. W12 may not need to be added. But it all makes sense. A very good explanation.
Same remark concerning W12, good job Krish Naik and thank you for your efforts
Hi Both, I also have same query
I think this part dL/dw11^2 should be (dL/dO31 *dO31/O21 *dO21/dO11^2). If we are taking derivative of dL w.r.t w11^2 then,w12^2 doesn't come into play. So,in that case, dL/dO12^2= (dL/dO31 *dO31/O22 *dO22/dw12^2)
agree...dw11^2 should be (dL/dO31 *dO31/O21 *dO21/dO11^2). not extra afte addition
Hi Krish, can you pls let me know, if we are calculating the derivative of W2 11 weight then why we are adding derivative of W2 12 weight in that. ? pls clear
yeah I did understand chain rule but being a fresher please provide some easy to study articles on chain rule so that i can increase my understanding before proceeding further.
but sir, In other source of internet, they are showing a different loss function. which 1 would i believe?
Hey Krish, god explanation
I think there is one correction. In the end, you explained for w11^2, what I feel is, it is for w11^1.
In the step where dL/dw[2]11 was shown as addition of two separate chain rule outputs, should it not be dL/dw[2]1 ?
thank you for great explanation,
i have a question, with this formula which generates for ( diff(L) / diff (W11)) is completely same for ( diff(L) / diff (W12))
i am i right? does both value gets same difference in weights while back propagation ( though W old value will be different
Same question.
What I think, as we are finding out the new weights, the W11 and W12 for HL2, both should be different and should not be added, or I am missing something.
@@SunnyKumar-tj2cy Yeah, Both should not be added as they are diff...
Yes i have same question too!
@@abhinaspadhi8351 its wrong
krish sir, is it w12^2 is depends on w11^2 then only we can do differentiation. w12^2 is going one way and w11^2 is going another way.
Do u update the bias during backpropagation along with weights? Or does it remain constant after the initialization?
Yes we have to update the bais too
here we used optimizer to update the weight slope is dl/dw so w here is w_old or something else.
Could you please recheck the video at around 11:00, W11 weight updation should be independent of W12.
a doubt in dL/dw11 is that correct?? we need to add?
If we are calculating the updated weight of W11^2 then why we need to add the weight W12^2 ?
We are solving supervised learning problem that's why we have loss as actual-predicted , what in case of unsupervised where we don't have y actual how the loss is calculated and how the updation happen
I don't think there will be back propogation in unsupervised learning!
how do you take the derivative of d(O31)/dO21? what kind of equations are those?
subscribed
for calculating the loss function wrt W112 why do you also consider the other branch leading to the output ?? Kindly reply
it's mentioned clearly that it's wrt only W112 - the reason I'm asking this question
Hey Krish, your way of explanation is good.
I think there is one correction. In the end, you explained for w11^2, what I feel is, it is for w11^1. It would be really helpful if you correct it because many are getting confused with it.
I think the same.. But great method of teaching.. there is no doubting that
Sir, O31 is also impacted by weight W11(3) ryt? why we are not taking that derivative in chain rule?
Hola. Sabes Redes nueronales (Neural networks) utilizando el software Statistica?
Please tell me what's that o represents
Great Video and a Great initiative sir
from 12:07 if we use same method to calculate dL/dW12^2 it will be the same as dL/dW11^2.
is this the correct way or am I getting it wrong
thank you!
Hi sir, Sorry to say you that which degree you have completed,you are awesome!
how can we cumpute dL/dO31 or what is the formula for to find dL/dO31 ?
10:44 you are pointing to w1_11, but why the formula on board is the derivative w.r.t w2_11?
That's correct.
Even I was wondering the same
Then what will be the formula for derivative of loss wrt w12^2 ?