Gradient Descent From Scratch in Python - Visual Explanation

Поделиться
HTML-код
  • Опубликовано: 15 ноя 2024

Комментарии • 42

  • @cerealport2726
    @cerealport2726 Год назад +16

    This is a very nice video explaining the mysteries behind gradient descent!
    The greek "n" looking symbol is eta, as far as I am aware.

  • @uchihamadara6519
    @uchihamadara6519 2 месяца назад +1

    Such an underrated video, explained Gradient Descent, GD 3d animation plotting using Matpplotlib, A TOP TIER VIDEO !!

  • @markosth09
    @markosth09 Год назад +13

    The greek letter "η" is called eta.

  • @ivanbg6908
    @ivanbg6908 4 месяца назад +3

    What compiler do you use? I use VSCode but I can not change the perspective of the 3DPlot. Thanks for the video.

  • @navsquid32
    @navsquid32 6 месяцев назад +1

    I’d recommend implementing a higher-order finite difference scheme for computing the gradient instead of hard-coding the analytic derivative for those who want to implement more general schemes.

  • @lilprotakeit
    @lilprotakeit Год назад +1

    Super Awesome .. Wonderful explanation and i can understand this video has some prerequisite .. but what you can do is leave some references to people who are not graduated to this level

  • @alibastami
    @alibastami 7 месяцев назад

    Thank you brother, this was immensely helpful

  • @sandipandutta8776
    @sandipandutta8776 6 месяцев назад

    at the end, when you plotted 3 points, you only adjusted the x and y coordinates, but did not change the z coordinate. it was still z_function(0.7, 0.4)

  • @dizoner2610
    @dizoner2610 Год назад +2

    I spent around 490 hours learning calc 3 , now I gotta implement this algorithm, thx u for explanation

    • @unknown__user__800
      @unknown__user__800 Год назад

      You counted the hours😮

    • @dizoner2610
      @dizoner2610 Год назад +2

      @@unknown__user__800 yeah I actually did just to see how productive (I guess I can say ) I am

  • @prashantm9856
    @prashantm9856 Год назад +2

    Very educational bro ,I love it❤

  • @InassInassaghil
    @InassInassaghil Месяц назад

    Which compiler are you using here ?

  • @mugen-one
    @mugen-one 7 месяцев назад

    Great explanation and good visuals!

  • @unknown-ie3ik
    @unknown-ie3ik Год назад +4

    Aaaawesome, as expected 🔥🔥
    Could you do logistic regression

  • @alanbal888
    @alanbal888 Год назад

    Thank you so much, it really helped me out understanding the gradient descent :)!!!

  • @nancybm41
    @nancybm41 Год назад +2

    thanks for the video. great job. I think you forgot to update the z function with the correct x and y values for positions 1-3.

  • @incrediblehuman1173
    @incrediblehuman1173 10 месяцев назад

    Thank you, very well explained 🙏

  • @thomas-mwaba
    @thomas-mwaba Год назад

    Thank you very much for the video 🙌🏽

  • @Mar-ts4bn
    @Mar-ts4bn 11 месяцев назад

    Is that work with multiple features datasets?

  • @introtoprogramming9162
    @introtoprogramming9162 Год назад

    Great Explanation..👍

  • @mohammedk8545
    @mohammedk8545 Год назад +1

    16:16 Rollercoaster !!

  • @unknown-ie3ik
    @unknown-ie3ik Год назад +1

    Thank you very much

  • @yakupkaanbaycan9316
    @yakupkaanbaycan9316 Год назад

    Great video, thanks

  • @Jallo224
    @Jallo224 3 дня назад

    Soo underrated 😢

  • @foodfunk6730
    @foodfunk6730 9 месяцев назад

    Awsm. When I run the code in colab, I get multiple plots. One plot for each iteration. It seems that plt.clf() is not clearing the plot. Can you please answer why its happening. Here is the code
    def y_function(x):
    return x**2
    def y_derivative(x):
    return 2*x
    x = np.arange(-100,100,0.1)
    y = y_function(x)
    current_pos = (80, y_function(80))
    learning_rate = 0.01
    for _ in range (100):
    new_x = current_pos[0] - learning_rate*y_derivative(current_pos[0])
    new_y = y_function(new_x)
    current_pos = (new_x,new_y )
    plt.plot(x, y)
    plt.scatter(current_pos[0], current_pos[1], color='red')
    plt.pause(0.1)
    plt.clf()

    • @garydixter4407
      @garydixter4407 9 месяцев назад

      I got the same issue
      did you find any solution?

  • @SteffCelTare
    @SteffCelTare 7 месяцев назад

    Love this video

  • @danielsehnoutek2016
    @danielsehnoutek2016 Год назад

    great tutorial

  • @TesfaldetBokretsion
    @TesfaldetBokretsion Год назад

    very clean

  • @swapnilnangare5805
    @swapnilnangare5805 6 месяцев назад

    I getting error in computed_zorder anyone is there any update

  • @sharjeel_mazhar
    @sharjeel_mazhar 6 месяцев назад

    Can anyone please teach me how to take the derivatives of this function: [sin(5x) * cos(5y)] / 5

  • @CodeHacker-v8x
    @CodeHacker-v8x Год назад

    Best tutorial ever seen

  • @ajeetsbpr
    @ajeetsbpr Год назад

    awesome bro

  • @thomasgoodwin2648
    @thomasgoodwin2648 Год назад

    Calcuwho? The progging I get (mostly). The maths (While I do understand the underlying principles) somehow always produce soup when I try it (a form of dyslexia). The cool part is that these days we have new tools to extend ourselves mentally (and not at all in any naughty ways like some of you might be thinking despite 40% of the internet being dedicated to porn) such as Wolphram Alpha and ChatGPT. Using such tools allows us to extend the boundaries imposed by our own personal mental limitations.
    To those of you who might be a bit more like me and fear treading the murky reef filled waters of higher maths remember that even if the mechanics elude you, a basic understanding is enough to use these tools to supplement ones capabilities. Even those who are well versed in math would be wise to make use of them given our roughly 15% error rates. Let the machine do the heavy lifting for the difficult and/or complicated bits.

  • @alfa_quest
    @alfa_quest Год назад

    Amazing

  • @vasupatel7013
    @vasupatel7013 Год назад

    Hey can you please guide me, I am at begginer level , I am trying to built a python script or model which can detect wheather a pdf is an image one or non image , I got stuck at one problem: even if pdf is non image because it contains some type of stamps in it , it is considering it as image file and I am unable to segregate files , can you please suggest what should i do in this case.

  • @applepie7282
    @applepie7282 Год назад

    thx

  • @hejrey6228
    @hejrey6228 Год назад

    10/10

  • @taruchitgoyal3735
    @taruchitgoyal3735 Год назад

    Hello Sir,
    When I execute: -
    ax=plt.subplot(projection="3d", computed_zorder=False)
    AttributeError: 'Axes3DSubplot' object has no property 'computed_zorder'
    Can you please suggest how to resolve the problem?
    Thank you