Awesome stuff. Searched this video because I was trying to figure out why the scores/sum scores approach wouldn't work and you addressed it first thing. Great job.
What a great explanation! Thank you very much. The why do we choose this formula versus this formula explanation is truly makes everything clear. Thank you once again :)
Thank you!!! This is so much clearer and straighter than 2 20-minutes videos on Softmax from "Machine Learning with Python-From Linear Models to Deep Learning" from MIT! To be fair, the latter explains multiple perspectives and is also good in its sense. But you deliver just the most importaint first bit of what is softmax and what are all these terms are about.
please note that the outputs of Softmax are NOT probabilities but are interpreted as probabilities. This is an important distinction! The same goes for the Sigmoid function. Thanks
well after applying sigmoid you get only one probability p (the other one you can calculate as 1-p) so actually you only need one number in case of sigmoid
Hey, thank you for a great video! I have a question: in your example, you said that probabilities between 0,1 and 2 should not be different from 100, 101, and 102. But in the real world, the scale which is used to assess students makes difference and affects probabilities. The difference between 101 and 102 is actually smaller than between 1 and 2, because in the first case the scale is probably much smaller, so the difference between scores is more significant. So wouldn't a model need to predict different probabilities depending on the assessment scale?
My point of view is that the softmax scenario is different from sigmoid scenario. In the sigmoid case, we need to capture the changes in relative scale because subtle changes around the 1/2 prob. point result in significant prob. changes(turns the whole thing around, drop out or not); whereas in the softmax case, there are more outputs and our goal is to select the very case which is most likely to happen, so we are talking about an absolute amount rather than a relative amount(final judge). I guess that's why ritvik said" change in constant shouldn't change our model'.
What does dP_i/dS_j = -P_i * P_j mean and how did you get it? I understand dP_i/dS_i because S_i is a single variable. But dP_i/DS_j is a whole set of variables (Sum(S_j) = S_1 + S_2 ... S_n) rather than a single one. How are you taking a derivative of that?
I am new to Data Sceince. However, why would a model output 100, 101 and 102 as three outputs unless the input had similarity to all three classes. Even in our daily lives, we would ignore 2 dollar variance on $100 think but complain if something which was originally free but now costs 2 dollars. Question is, why would we give up the usual practice and use some fancy transformation function here ?
Oh.. softmax is for multiple classes and sigmoid is for two classes. I get that your i here is the class. In the post below though, is their i observations and k the classes? stats.stackexchange.com/questions/233658/softmax-vs-sigmoid-function-in-logistic-classifier
are you crazy. the moment he did that, I knew it would be fun listening to him. He was focused. Like he said, theory is relevant only in context of practicality.
4:00 I thank you have express it in a wrong way you wanted to say that we need to go into depth and not just focus on the application that is the façade which here's deriving formula
tutorials with boards noww...nice one dude...underrated channel I must say!
Much appreciated!
agreed. greetings from russia!
I really love how you progress step by step instead of directly throwing out the formulas! The best video on UA-cam on the Softmax! +1
For a non-mathematician like myself, this was crystal clear, thanks very much!
Awesome stuff. Searched this video because I was trying to figure out why the scores/sum scores approach wouldn't work and you addressed it first thing. Great job.
An excellent and straightforward way of explaining. So helpful! Thanks a lot :)
The only video I needed to understand the SOFTMAX function. Kudos to you!!
What a great explanation! Thank you very much.
The why do we choose this formula versus this formula explanation is truly makes everything clear. Thank you once again :)
What an amazing, simple explanation. thank you!
Great explenations, your addition of the story to the objects really help understanding the material
This is excellent! I saw your video on the sigmoid function and both of these explain the why behind their usage.
Glad it was helpful!
the person who is going to be responsible for me kick starting my ML journey with a good head on my shoulders, thank you ritvik, very enlightening
Great explanation! Easy and helpful!
The introduction to softmax which explains why softmax exists helped me a lot understanding it
thank you very much, you are very good at teaching, very well prepared!
Woooow ,really liked our teaching approach, awesome!
Great explanation, thank you!
Awesome explanation.... thanks !!!
Very clear explained , thank you, subscribed
You're amazing. great teacher
Thanks for such intuitive explanation Sir :)
How great was this video! thank you
Beautiful!
Very clearly explained!
Thanks Professor!
Absolutely beautiful.
Dude! I really love you.
Wow...teaching from first principles...I love that!
Glad you liked it!
Awesome Brother!
Thank you!!! This is so much clearer and straighter than 2 20-minutes videos on Softmax from "Machine Learning with Python-From Linear Models to Deep Learning" from MIT! To be fair, the latter explains multiple perspectives and is also good in its sense. But you deliver just the most importaint first bit of what is softmax and what are all these terms are about.
Glad it helped!
Clearest explanation about softmax.. thank you
Glad it was helpful!
Solid video, subscribed!
Just great! Thanks, man.
You're welcome!
Thank you so much! You made it very clear :)
Bravo! + Thank you very much!
Thnx. Very clear explanation of the rationale for employing exponential fns instead of linear fns
Great to hear!
Now i know why lot of your videos answers WHY question. You give importance to application not the theory alone. concept is very clear. thanks
Very helpful!!! Thx!
Amazing!
I came for the good-looking teacher but stayed for the really clear an good explanation.
I like the hierarchy implied by the indices on the S vector ;)
Thank you very much, clear and helpful to me as a beginer😗
Thank you so much. I now understand why exp is used instead of simple calc.😊
Of course!
I wish you were my teacher haha great explanation :D Thank you so much ♥
awesome man..your videos make me less anxious about math..
You can do it!
that was so much sweet and inspiring
thank you so much !!
bro you're a legend
thank you!
Could you do a video about the maxout unit? I read it on Goodfellow's Deep Learning book, but I did not grasp the intuition behind it clearly.
Keep going buddy
good video
a clear explanation!
Glad you think so!
Thank you
Holy shit! That makes so much sense
Nice video
PRETTY GOOD
more people should watch this
Thanks 👍
No problem 👍
Very good video
Thanks!
3:18 very good teacher
thanks
Do you do one on one tutoring?
hi there, what is the meaning of the square summation?
please note that the outputs of Softmax are NOT probabilities but are interpreted as probabilities. This is an important distinction! The same goes for the Sigmoid function. Thanks
You teach better than my grad school professor 😂
👍🏻👍🏻👍🏻👍🏻👍🏻👍🏻
@ritwikmath want to understand why you chose the subscript N to describe the features; they should be S_1..S_M isn't it?
Yet again an Indian dude is saving me!
Lol 😂
1:14, how is it a single dimensional for sigmoid? Shouldn't it be two dimensions?
well after applying sigmoid you get only one probability p (the other one you can calculate as 1-p) so actually you only need one number in case of sigmoid
How to dealing with high Xi values? I got 788, 732 for Xi value, and if I exp(788) it gives error bcs it exp results near to infinity
Hey, thank you for a great video! I have a question: in your example, you said that probabilities between 0,1 and 2 should not be different from 100, 101, and 102. But in the real world, the scale which is used to assess students makes difference and affects probabilities. The difference between 101 and 102 is actually smaller than between 1 and 2, because in the first case the scale is probably much smaller, so the difference between scores is more significant. So wouldn't a model need to predict different probabilities depending on the assessment scale?
same question!
My point of view is that the softmax scenario is different from sigmoid scenario. In the sigmoid case, we need to capture the changes in relative scale because subtle changes around the 1/2 prob. point result in significant prob. changes(turns the whole thing around, drop out or not); whereas in the softmax case, there are more outputs and our goal is to select the very case which is most likely to happen, so we are talking about an absolute amount rather than a relative amount(final judge). I guess that's why ritvik said" change in constant shouldn't change our model'.
Maybe this was explained in a past video, but why is "e" chosen over any other base (like 2 or 3 or pi)...
What does dP_i/dS_j = -P_i * P_j mean and how did you get it? I understand dP_i/dS_i because S_i is a single variable. But dP_i/DS_j is a whole set of variables (Sum(S_j) = S_1 + S_2 ... S_n) rather than a single one. How are you taking a derivative of that?
Hello Boltzmann distribution we meet again, cool nickname
I am new to Data Sceince. However, why would a model output 100, 101 and 102 as three outputs unless the input had similarity to all three classes. Even in our daily lives, we would ignore 2 dollar variance on $100 think but complain if something which was originally free but now costs 2 dollars. Question is, why would we give up the usual practice and use some fancy transformation function here ?
I don't understand *why* it's weird that 0 maps to 0 or why we need the probability to be the same for a constant shift...
what a shame that this dude is not a professor!!!!!!!!
Oh.. softmax is for multiple classes and sigmoid is for two classes.
I get that your i here is the class. In the post below though, is their i observations and k the classes?
stats.stackexchange.com/questions/233658/softmax-vs-sigmoid-function-in-logistic-classifier
god
I knew things were about to go down when he flipped the pen.
are you crazy. the moment he did that, I knew it would be fun listening to him. He was focused. Like he said, theory is relevant only in context of practicality.
Very different from how *cough* Siraj *cough* explained this lol
4:00 I thank you have express it in a wrong way you wanted to say that we need to go into depth and not just focus on the application that is the façade which here's deriving formula
Why do I need to go to school?
Binod stop ads
minute 11-12.30 you are not very clear and going too fast
hey thanks for the feedback, will work on it