The Softmax : Data Science Basics

[@wennie2939]

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

[@birajkoirala5383]

tutorials with boards noww...nice one dude...underrated channel I must say!

[@ritvikmath]

Much appreciated!

[@MrDullBull]

agreed. greetings from russia!

[@DFCinBE]

For a non-mathematician like myself, this was crystal clear, thanks very much!

[@akum007]

I love it! The choice of examples and the way you explain ... just bravo!

[@ritvikmath]

Thank you! 😃

[@debapriyabanerjee8486]

This is excellent! I saw your video on the sigmoid function and both of these explain the why behind their usage.

[@ritvikmath]

Glad it was helpful!

[@omniscienceisdead8837]

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

[@okeuwechue9238]

Thnx. Very clear explanation of the rationale for employing exponential fns instead of linear fns

[@ritvikmath]

Great to hear!

[@marcusakiti7608]

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.

[@iraklisalia9102]

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 :)

[@MORE2Clay]

The introduction to softmax which explains why softmax exists helped me a lot understanding it

[@suparnaprasad8187]

This channel is literally the best.

[@ritvikmath]

Thanks!

[@zvithaler9443]

Great explenations, your addition of the story to the objects really help understanding the material

[@ekaterinakorneeva4792]

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.

[@ritvikmath]

Glad it helped!

[@ManpreetKaur-ve5gw]

The only video I needed to understand the SOFTMAX function. Kudos to you!!

[@zafarnasim9267]

Woooow ,really liked our teaching approach, awesome!

[@vamshi755]

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

[@johnlabarge]

This is a glorious explanation.

[@somteezle1348]

Wow...teaching from first principles...I love that!

[@ritvikmath]

Glad you liked it!

[@karimamakhlouf2411]

An excellent and straightforward way of explaining. So helpful! Thanks a lot :)

[@rizkysyahputra98]

Clearest explanation about softmax.. thank you

[@ritvikmath]

Glad it was helpful!

[@grzegorzchodak]

Great explanation! Easy and helpful!

[@YAlsadah]

What an amazing, simple explanation. thank you!

[@cobertizo]

I came for the good-looking teacher but stayed for the really clear an good explanation.

[@salmans1224]

awesome man..your videos make me less anxious about math..

[@ritvikmath]

You can do it!

[@MLDawn]

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

[@shiyuyuan7958]

Very clear explained , thank you, subscribed

[@michael88704]

I like the hierarchy implied by the indices on the S vector ;)

[@serdarufukkara7109]

thank you very much, you are very good at teaching, very well prepared!

[@AIPeerAcademy]

Thank you so much. I now understand why exp is used instead of simple calc.😊

[@ritvikmath]

Of course!

[@bryany7344]

1:14, how is it a single dimensional for sigmoid? Shouldn't it be two dimensions?

[@vahegizhlaryan5052]

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

[@maralazizi]

Another great content, thank you so much!

[@ritvikmath]

My pleasure!

[@masster_yoda]

Great explanation, thank you!

[@fatemehsefishahpar3626]

How great was this video! thank you

[@debaratiray2482]

Awesome explanation.... thanks !!!

[@nehathakur8221]

Thanks for such intuitive explanation Sir :)

[@karimomrane7556]

I wish you were my teacher haha great explanation :D Thank you so much ♥

[@Nova-Rift]

You're amazing. great teacher

[@aFancyFatFish]

Thank you very much, clear and helpful to me as a beginer😗

[@eliaslara6964]

Dude! I really love you.

[@anandiyer5361]

@ritwikmath want to understand why you chose the subscript N to describe the features; they should be S_1..S_M isn't it?

[@bittukumar-rv6rx]

Thank s for uploading ❤❤❤

[@jackshaak]

Just great! Thanks, man.

[@ritvikmath]

You're welcome!

[@seojun2599]

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

[@bhp72]

really enjoyed that. thanks!

[@ManishaGupta-rj3bq]

Great tutorials!

[@ritvikmath]

Glad you like them!

[@burger_kinghorn]

How does this relate to multinomial logistic regression?

[@igoroliveira5463]

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.

[@yingchen8028]

more people should watch this

[@d_b_]

Maybe this was explained in a past video, but why is "e" chosen over any other base (like 2 or 3 or pi)...

[@zahra_az]

that was so much sweet and inspiring

[@zacharydan7236]

Solid video, subscribed!

[@kausshikmanojkumar2855]

Absolutely beautiful.

[@jeeezsh4704]

You teach better than my grad school professor 😂

[@diegosantosuosso806]

Thanks Professor!

[@ヨママ]

Thank you so much! You made it very clear :)

[@dikshanegi1028]

Keep going buddy

[@tm0209]

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?

[@mrahsanahmad]

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 ?

[@oligneflix6798]

bro you're a legend

[@dragolov]

Bravo! + Thank you very much!

[@ridhampatoliya4680]

Very clearly explained!

[@sukursukur3617]

3:18 very good teacher

[@jasonokoro8400]

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...

[@kavitmehta9143]

Awesome Brother!

[@ZimoNitrome]

good video

[@shreyasshetty6850]

Holy shit! That makes so much sense

[@kausshikmanojkumar2855]

Beautiful!

[@evagao9701]

hi there, what is the meaning of the square summation?

[@suyashdixit682]

Yet again an Indian dude is saving me!

[@ritvikmath]

Lol 😂

[@johnginos6520]

Do you do one on one tutoring?

[@mmm777ization]

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

[@azinkatiraee6684]

a clear explanation!

[@ritvikmath]

Glad you think so!

[@markomarkus8560]

Nice video

[@peterniederl3662]

Very helpful!!! Thx!

[@yuchenzhao6411]

Very good video

[@ritvikmath]

Thanks!

[@Fat_Cat_Fly]

👍🏻👍🏻👍🏻👍🏻👍🏻👍🏻

[@evgenyv5687]

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-mb1ih]

same question!

[@imingtso6598]

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'.

[@ltang]

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

[@wduandy]

Amazing!

[@brendanamuh5683]

thank you so much !!

[@ayeddie6788]

PRETTY GOOD

[@tsibulsky4900]

Thanks 👍

[@ritvikmath]

No problem 👍

[@matgg8207]

what a shame that this dude is not a professor!!!!!!!!

[@joelpaddock5199]

Hello Boltzmann distribution we meet again, cool nickname

[@hezhu482]

thank you!

[@anishbabus576]

Thank you

[@y0n1n1x]

thanks

[@jkhhahahhdkakkdh]

Very different from how *cough* Siraj *cough* explained this lol

[@QiyuanSong]

Why do I need to go to school?

[@gestucvolonor5069]

I knew things were about to go down when he flipped the pen.

[@mrahsanahmad]

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.

[@srl2017]

god

[@suryatejakothakota7742]

Binod stop ads

[@fintech1378]

minute 11-12.30 you are not very clear and going too fast

[@ritvikmath]

hey thanks for the feedback, will work on it