Stochastic Gradient Descent

Поделиться
HTML-код
  • Опубликовано: 1 ноя 2024

Комментарии • 54

  • @ADESHKUMAR-yz2el
    @ADESHKUMAR-yz2el Год назад +56

    feels illegal to watch such great content for free

  • @aj_ai
    @aj_ai Год назад +44

    Life is stochastic gradient descent:
    - Thrashing? Slow down.
    - Stuck in a rut? Change your learning rate.
    - Once you get going, momentum carries you.
    - Not every step you take is in the right direction, but trust the process to get you where you need to go.

  • @Ravi-sl5ms
    @Ravi-sl5ms 3 года назад +40

    You are so skilled; you really know how to teach such complicated topics with such ease. Glad to found your channel. will recommend it to all my friends trying to learn machine learning.. Thank you.

  • @visheshmp
    @visheshmp 10 месяцев назад +7

    after completing more than 50 videos of playlist now I like videos then I watch it.

  • @gamersgame43
    @gamersgame43 11 месяцев назад +2

    28:00 the major time difference concept between the two versions of Gradient Descent is explained so well that I can never forget it

  • @ytg6663
    @ytg6663 3 года назад +11

    Best sir ho aap...
    👍👍 May you touch skies in Life😎😎😎

  • @arpitakar3384
    @arpitakar3384 Месяц назад +2

    27:38 the smile when SGD gave More Time......
    Then well Defended ::: HERO

  • @marselwidianto4387
    @marselwidianto4387 2 года назад +1

    You have such an important skill will recommend your channel to my frnd

  • @karangupta3491
    @karangupta3491 Год назад +1

    One of the BEST mentor out there

  • @ShreenaGhoshal-uy6nt
    @ShreenaGhoshal-uy6nt 2 месяца назад

    You are very underrated sir... Hats off to your efforts

  • @editor_india_2024
    @editor_india_2024 2 года назад +4

    Best explanation!!
    Sir please explain about other optimizer like adam, adagrad etc

  • @arindamInsightFullMath
    @arindamInsightFullMath Месяц назад

    sir nothing to say as always best .....u are a great teacher ...💕💕💕💕💕💕💕💕

  • @badalrathod2435
    @badalrathod2435 2 года назад +1

    very good teaching and explaination....thanks!

  • @hasanrants
    @hasanrants Месяц назад

    thanks Sir Nitish.
    completed on 13th September 2024, 10:15PM

  • @ParthivShah
    @ParthivShah 7 месяцев назад +3

    Thank You Sir.

  • @ADESHKUMAR-yz2el
    @ADESHKUMAR-yz2el Год назад +1

    God level teaching

  • @lijindurairaj2982
    @lijindurairaj2982 2 года назад +1

    GOD bless you, your videos are very helpful :)

  • @thatsfantastic313
    @thatsfantastic313 Год назад +1

    best explanation!

  • @GovindaArya-fe7kr
    @GovindaArya-fe7kr 3 месяца назад

    Really very helpful, great

  • @Gudduyadav_1989
    @Gudduyadav_1989 3 месяца назад

    Amazing 😮.. thank you so so much

  • @abdulqadar9580
    @abdulqadar9580 Год назад +2

    Great Video Great Teacher

  • @sujithsaikalakonda4863
    @sujithsaikalakonda4863 2 года назад

    Great Explanation sir.

  • @vishwjoshi853
    @vishwjoshi853 2 месяца назад

    So, if the value of idx gets repeated like it's random then will it just keep updating the gradients of same row? BTW, great explaination sir.

  • @Ishant875
    @Ishant875 9 месяцев назад

    36:50 If the line is not crossing the curve, it can also be a concave curve.

  • @hardik3809
    @hardik3809 День назад +1

    I HAVE A DOUBT:
    Agar learning schedules use karenge to learning rate decrease karega after every epoch. But agar hamara function non-convex hua, to uss case mei chance badh jaega ki vo local minima par hi stuck ho jae aur global minima tak na pahunch paye. Kyunki learning rate decrease karega to vo kam deviate karega.
    Does this mean that learning schedules are not good for non-convex functions?
    Please reply if anyone knows about it..

  • @tech_inspiration
    @tech_inspiration Месяц назад

    Love this

  • @proveerghosh5183
    @proveerghosh5183 2 года назад +2

    just a thing suppose for 10 epochs and 100 rows batch gd will perform 1000 iterations and similarly sgd will also perform 1000 iteration i think maybe due to np.dot over entire matrix works fast therefore batch gd is faster than sgd for same epochs

    • @123arskas
      @123arskas Год назад +1

      The process of updating parameters (coeffs and intercept) for each row takes more time in SGD. GD will update them only 10 times meanwhile SGD have to update them 1000 times. Thus at such a low dataset SGD is slow.

  • @syedaafreen1075
    @syedaafreen1075 3 месяца назад

    Amazing

  • @BharatJain-bl5gw
    @BharatJain-bl5gw 3 года назад

    Here come the saviour 👍❤️❤️❤️

  • @shivanshgoel2504
    @shivanshgoel2504 4 месяца назад +1

    plz provide all of the notes that you write on One note day vise

  • @ahmadtalhaansari4456
    @ahmadtalhaansari4456 Год назад +4

    Revising my concepts.
    July 29, 2023😅

  • @anshkapoor4990
    @anshkapoor4990 6 месяцев назад

    No words for you❤

  • @heaven-aman5946
    @heaven-aman5946 10 дней назад

    Bestest❤

  • @mukandarsikandar1062
    @mukandarsikandar1062 8 месяцев назад

    Sir if I don't use random index I just put 'i' so its give same result also not varry when I run it multiple time??
    So can we use it??

  • @mohitkushwaha8974
    @mohitkushwaha8974 Год назад +1

    Sir, do i need to write the complte code if i want to use the batch gradient descent?

    • @ashwinjain5566
      @ashwinjain5566 Год назад

      you can use, for example, the SGDRegressor from sklearn.

  • @tanmayshinde7853
    @tanmayshinde7853 3 года назад

    what if we dont pick random points in stochastic G D ?

  • @Sara-fp1zw
    @Sara-fp1zw 3 года назад

    thankyou!!

  • @priyam8665
    @priyam8665 Месяц назад

    done✅

  • @shrutigarg9081
    @shrutigarg9081 Год назад

    ❤❤

  • @tanmayshinde7853
    @tanmayshinde7853 3 года назад

    TypeError Traceback (most recent call last)
    in
    ----> 1 reg.fit(X_train,y_train)
    TypeError: fit() missing 1 required positional argument: 'y'
    am getting this type of error . can any one help?

  • @messi0510
    @messi0510 Год назад +1

    1:25 Problem with batch gradient descent

  • @mylofiworld9979
    @mylofiworld9979 3 месяца назад

  • @murumathi4307
    @murumathi4307 3 года назад

    I am already get 43% normal linear regression method..ofter I used GD at tha same 43% ..why I am use GD ,lot of code ?

    • @campusx-official
      @campusx-official  3 года назад +2

      GD is used in the case of large datasets. Since it is faster

  • @ShaanBlog
    @ShaanBlog 3 года назад +4

    Khan sir duplicate 😍❤️🤭

  • @rb4754
    @rb4754 5 месяцев назад

    SGD is stochastic but your high teaching standard is static...

  • @RohanOxob
    @RohanOxob 2 года назад

    31:45

  • @priyaranjanilfs8854
    @priyaranjanilfs8854 Год назад

    Sir if the batch gradient descent is not useful than why did you teach one hour