@@thepresistence5935 but honestly as a beginner it's really hard to understand from Andrew ng , I can grasp very topics from krish very easily (I'm in 9th class).
Krish there is correction @15:49 you said Squared error loss as Mean Squared Error loss (when we divide with sample number then it will be MSE). You have corrected it at 27:44, thanks!
@18:57 sir i think that it has been squared not only to penalize the high error but also to account for the fact that if error is not squared,then if for one record the error is positive and for other it is negative then if we add them without squaring then total error will show to be reduced,when infact it is not that way
we enjoyed the paid class freely, thankyou Krish sir, please create a playlist and upload paid class videos please, it's very useful for us 😂😂😂😂, and it's easy to understand during online classes. ( I got a deeper understanding of optimization and loss function thanks!)
Please don't have such a mindset. This is called community service if someone in the community is blessed he should contribute to and make it available for the less blessed people. So simply put if you are blessed contribute to the channel. thanks Krish and everyone who contributes for the community. take care brother don't get me wrong. if i have or may said anything incorrect i am open to all opinions and correction. I am just another man.
How squaring a loss function penalises the model. I think squaring is performed to ensure that negative values of loss function do not cancel out positive values and we get false indication that our loss function is very small.
if error between y and y^ is 4, then loss will be square of 4. so by squaring it gets more penalised and if error is less than 1, ie 0.4 then its square is 0.16 so less penalised
sir i have a doubt , i think we should select the correct class's probability rather than selecting the highest probability after softmax in y hat... please correct me if i am wrong .
Answer I found, correct me if wrong. It makes the math easier to handle. Adding a half or not doesn't actually matter since minimizing is unaffected by constants
Rest of the World : We have Andrew Ng for Teach AI
India : We have Krish Naik 🔥
100% right
its true he is the one of the boon for our nation
As an educator Krish Naik >> Andrew Ng
@@RTC1655 haa dude both are good, please don't compare. but i love krish
@@thepresistence5935 but honestly as a beginner it's really hard to understand from Andrew ng , I can grasp very topics from krish very easily (I'm in 9th class).
Krish there is correction @15:49 you said Squared error loss as Mean Squared Error loss (when we divide with sample number then it will be MSE). You have corrected it at 27:44, thanks!
One of the Best Teachers in India . He'll make the concept simple and clear .Great teaching skills
for some apparent reason i have started to binge watch these
@18:57 sir i think that it has been squared not only to penalize the high error but also to account for the fact that if error is not squared,then if for one record the error is positive and for other it is negative then if we add them without squaring then total error will show to be reduced,when infact it is not that way
1/m should be Mean square error. M would be the number of batch size. Isn't it?
so nicely u explained the differences between tensorflow versions . Thanks . They ask this in interview too
Amazing tutorial....excellent work....thanks for the content
superb clarity i got
we enjoyed the paid class freely, thankyou Krish sir, please create a playlist and upload paid class videos please, it's very useful for us 😂😂😂😂, and it's easy to understand during online classes. ( I got a deeper understanding of optimization and loss function thanks!)
Please don't have such a mindset. This is called community service if someone in the community is blessed he should contribute to and make it available for the less blessed people. So simply put if you are blessed contribute to the channel. thanks Krish and everyone who contributes for the community. take care brother don't get me wrong. if i have or may said anything incorrect i am open to all opinions and correction. I am just another man.
@@moindalvs It's ok no worries. :) I thought it's a paid class for some students.
😅😅 1:08:44 😮😮h 1:09:26 bjjnjhjjhhuugvhjvhj😂ijnkjkkoj@@moindalvs
At 15:09, Instead of MSE it's actually SSE.
Sir want a video on metrics of accuracies.
When are we getting next part of this? The development part?
one small correction, MSE is 1/n summation (y-y^)2
Krish, how Scientists came up with Cross Entropy Losses and why are they named so ?????
Sir make next tutorial for object detection TENSORFLOW
if layer >40 then we use swish activation function
How squaring a loss function penalises the model. I think squaring is performed to ensure that negative values of loss function do not cancel out positive values and we get false indication that our loss function is very small.
if error between y and y^ is 4, then loss will be square of 4. so by squaring it gets more penalised and if error is less than 1, ie 0.4 then its square is 0.16 so less penalised
This is what I was waiting for!
How MSE loss penalizer is different from regularisation?
can't we use number directly for target like 1, 2, 3 instead of one hot encoding.
Krish can you please upload a video on how create environment please
Please make a tutorial on What is the difference between model error and model risk?
Could you please cover deep learning loss function in class imbalanced ( focal loss, weighted cross entropy)
Mr. Krish where can I find the note of this lecture?
Hi Krish, You are videos are awesome, I am almost 1/4 done and have learned so much. I had one questions, is DSA a prerequisite for this ?
Yes, while implementing algos u require, basic is enough tho
Quadratic equation is non-linear algebra
how can we also get into the meeting
why we divide 2 while calculating the loss function?
it's basically 1/n where n is no. of samples in a batch
Krish...can you explain Probability as well
I was asked in interview why squared and not mean cubed error and despite of watching this video i couldn't recollect during interview😢😢
Dear Krish, can we define loss function with constraints like in optimization algorithms ?
Thank you
sir i have a doubt , i think we should select the correct class's probability rather than selecting the highest probability after softmax in y hat... please correct me if i am wrong .
in sparse cat cross entropy....
Good one sir
why 1/2 is considering in front of loss function?
Answer I found, correct me if wrong.
It makes the math easier to handle. Adding a half or not doesn't actually matter since minimizing is unaffected by constants
Hello 👋🤓💓
thankyou sir.....
U have steam do u play csgo or anything else ?? 🔥🔥
Ok both👍
great explanation but for me, it's very confusing.
krish i wanted to buy your materials ... i couldn't with my debit card kindly let me know an alternate
Try to join membership using gpay....search in youtube how to do it
thank you let me try the same ..
Good topic
Very informative lesson Krish!! But, At 48:20 should'nt there be weights connected to the output layer before applying the softmax function?
Yes👍
Yes
Great
❤❤❤❤❤❤❤❤❤❤
wow