I really love how you progress step by step instead of directly throwing out the formulas! The best video on KZbin on the Softmax! +1
@birajkoirala53834 жыл бұрын
tutorials with boards noww...nice one dude...underrated channel I must say!
@ritvikmath4 жыл бұрын
Much appreciated!
@MrDullBull3 жыл бұрын
agreed. greetings from russia!
@DFCinBE10 ай бұрын
For a non-mathematician like myself, this was crystal clear, thanks very much!
@debapriyabanerjee84863 жыл бұрын
This is excellent! I saw your video on the sigmoid function and both of these explain the why behind their usage.
@ritvikmath3 жыл бұрын
Glad it was helpful!
@iraklisalia91023 жыл бұрын
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 :)
@marcusakiti7608 Жыл бұрын
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.
@ekaterinakorneeva479210 ай бұрын
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.
@ritvikmath10 ай бұрын
Glad it helped!
@omniscienceisdead88372 жыл бұрын
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
@zvithaler94432 жыл бұрын
Great explenations, your addition of the story to the objects really help understanding the material
@MORE2Clay2 жыл бұрын
The introduction to softmax which explains why softmax exists helped me a lot understanding it
@okeuwechue92385 ай бұрын
Thnx. Very clear explanation of the rationale for employing exponential fns instead of linear fns
@ritvikmath5 ай бұрын
Great to hear!
@ManpreetKaur-ve5gw3 жыл бұрын
The only video I needed to understand the SOFTMAX function. Kudos to you!!
@masster_yoda6 ай бұрын
Great explanation, thank you!
@MTech-DataScience Жыл бұрын
Thank you so much. I now understand why exp is used instead of simple calc.😊
@ritvikmath Жыл бұрын
Of course!
@michael887042 жыл бұрын
I like the hierarchy implied by the indices on the S vector ;)
Wow...teaching from first principles...I love that!
@ritvikmath3 жыл бұрын
Glad you liked it!
@karimamakhlouf2411 Жыл бұрын
An excellent and straightforward way of explaining. So helpful! Thanks a lot :)
@rizkysyahputra983 жыл бұрын
Clearest explanation about softmax.. thank you
@ritvikmath3 жыл бұрын
Glad it was helpful!
@diegosantosuosso80611 ай бұрын
Thanks Professor!
@kausshikmanojkumar285511 ай бұрын
Beautiful!
@YAlsadah2 жыл бұрын
What an amazing, simple explanation. thank you!
@grzegorzchodak Жыл бұрын
Great explanation! Easy and helpful!
@vamshi7553 жыл бұрын
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
@cobertizo3 жыл бұрын
I came for the good-looking teacher but stayed for the really clear an good explanation.
@salmans12243 жыл бұрын
awesome man..your videos make me less anxious about math..
@ritvikmath3 жыл бұрын
You can do it!
@serdarufukkara71093 жыл бұрын
thank you very much, you are very good at teaching, very well prepared!
@debaratiray24822 жыл бұрын
Awesome explanation.... thanks !!!
@jackshaak3 жыл бұрын
Just great! Thanks, man.
@ritvikmath3 жыл бұрын
You're welcome!
@shiyuyuan79582 жыл бұрын
Very clear explained , thank you, subscribed
@dragolov2 жыл бұрын
Bravo! + Thank you very much!
@fatemehsefishahpar36263 жыл бұрын
How great was this video! thank you
@eliaslara69643 жыл бұрын
Dude! I really love you.
@MLDawn3 жыл бұрын
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
@Nova-Rift3 жыл бұрын
You're amazing. great teacher
@oligneflix67982 жыл бұрын
bro you're a legend
@ridhampatoliya46803 жыл бұрын
Very clearly explained!
@nehathakur82213 жыл бұрын
Thanks for such intuitive explanation Sir :)
@azinkatiraee6684 Жыл бұрын
a clear explanation!
@ritvikmath Жыл бұрын
Glad you think so!
@dikshanegi102810 ай бұрын
Keep going buddy
@aFancyFatFish3 жыл бұрын
Thank you very much, clear and helpful to me as a beginer😗
@karimomrane7556 Жыл бұрын
I wish you were my teacher haha great explanation :D Thank you so much ♥
@yingchen80283 жыл бұрын
more people should watch this
@brendanamuh5683 Жыл бұрын
thank you so much !!
@bryany73443 жыл бұрын
1:14, how is it a single dimensional for sigmoid? Shouldn't it be two dimensions?
@vahegizhlaryan50523 жыл бұрын
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
@markomarkus85603 жыл бұрын
Nice video
@tsibulsky4900 Жыл бұрын
Thanks 👍
@ritvikmath Жыл бұрын
No problem 👍
@korwi73732 жыл бұрын
thanks
@user-mf3sm2ds7j4 жыл бұрын
Thank you so much! You made it very clear :)
@zacharydan72363 жыл бұрын
Solid video, subscribed!
@ayeddie67882 жыл бұрын
PRETTY GOOD
@seojun259910 ай бұрын
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
@sukursukur36174 жыл бұрын
3:18 very good teacher
@shreyasshetty68503 жыл бұрын
Holy shit! That makes so much sense
@ZimoNitrome3 жыл бұрын
good video
@anandiyer53612 жыл бұрын
@ritwikmath want to understand why you chose the subscript N to describe the features; they should be S_1..S_M isn't it?
@zahra_az2 жыл бұрын
that was so much sweet and inspiring
@kavitmehta91434 жыл бұрын
Awesome Brother!
@d_b_ Жыл бұрын
Maybe this was explained in a past video, but why is "e" chosen over any other base (like 2 or 3 or pi)...
@peterniederl36623 жыл бұрын
Very helpful!!! Thx!
@tm02097 ай бұрын
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?
@suyashdixit682 Жыл бұрын
Yet again an Indian dude is saving me!
@ritvikmath Жыл бұрын
Lol 😂
@jasonokoro8400 Жыл бұрын
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...
@jeeezsh47042 жыл бұрын
You teach better than my grad school professor 😂
@Fat_Cat_Fly3 жыл бұрын
👍🏻👍🏻👍🏻👍🏻👍🏻👍🏻
@wduandy4 жыл бұрын
Amazing!
@anishbabus5764 жыл бұрын
Thank you
@igoroliveira54633 жыл бұрын
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.
@hezhu4824 жыл бұрын
thank you!
@mrahsanahmad3 жыл бұрын
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 ?
@yuchenzhao64114 жыл бұрын
Very good video
@ritvikmath4 жыл бұрын
Thanks!
@evagao97014 жыл бұрын
hi there, what is the meaning of the square summation?
@johnginos65204 жыл бұрын
Do you do one on one tutoring?
@joelpaddock51997 ай бұрын
Hello Boltzmann distribution we meet again, cool nickname
@evgenyv56873 жыл бұрын
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?
@EW-mb1ih2 жыл бұрын
same question!
@imingtso65982 жыл бұрын
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'.
@matgg82072 жыл бұрын
what a shame that this dude is not a professor!!!!!!!!
@ltang3 жыл бұрын
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
@mmm777ization3 жыл бұрын
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
@srl20172 жыл бұрын
god
@QiyuanSong Жыл бұрын
Why do I need to go to school?
@gestucvolonor50693 жыл бұрын
I knew things were about to go down when he flipped the pen.
@mrahsanahmad3 жыл бұрын
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.
@jkhhahahhdkakkdh3 жыл бұрын
Very different from how *cough* Siraj *cough* explained this lol
@suryatejakothakota77423 жыл бұрын
Binod stop ads
@fintech1378 Жыл бұрын
minute 11-12.30 you are not very clear and going too fast