Handwritten Digit Classification using ANN | MNIST Dataset

Поделиться
HTML-код
  • Опубликовано: 25 дек 2024

Комментарии • 110

  • @Pushpraj_gour
    @Pushpraj_gour 9 месяцев назад +17

    It's hard to express in words how good your teaching method is, and thank you for providing all these material for free.

  • @JohnWickea
    @JohnWickea 10 месяцев назад +7

    man your'e awesome . Even my MIT teachers fails to explains like you did. They just keep on saying blah blah blah didn't care whether anyone is understanding anything. Your'e a gem

  • @payelbanik
    @payelbanik 2 года назад +19

    Your concept is crystal clear, your teaching style is superb. Hats off to you Sir.

  • @tanmayshinde7853
    @tanmayshinde7853 2 года назад +23

    Sir, your efforts have to be appreciated cause you wake up early in the morning and make videos for us. Thank You, Thank You So Much!

  • @pankajbeldar9799
    @pankajbeldar9799 2 года назад +39

    You are billions times better than my IIT professor

    • @jainpratham8217
      @jainpratham8217 8 месяцев назад

      i agreeeeee

    • @elonmusk4267
      @elonmusk4267 6 месяцев назад

      totally agree

    • @saptarshisanyal6738
      @saptarshisanyal6738 4 месяца назад +2

      Totally agree, I have tried doing the deep learning course by prof Mitesh Khapra of IIT M, he may have post doc, he may have very in depth knowledge, but when it comes to explain the difficult concept to "not so brilliant" students, he fails. Whereas Nitish sir explains it so easily that even an average student is able to understand.

  • @singh6315
    @singh6315 2 года назад +10

    Thank You please don't stop making videos your knowledge is adding a lot of values in our life

  • @ywbc1217
    @ywbc1217 Год назад +3

    VERY GOOD ! 💪
    you are totally right
    link to colab is everything we need in description of video

  • @jaydeepjha3191
    @jaydeepjha3191 2 года назад +6

    amazing content sir I just wanted to learn ANN from you and here you upload it . thankyou sir

  • @kavitachaudhary2371
    @kavitachaudhary2371 Месяц назад +1

    Your teaching is so addictive , i cant distract even i if i try , thank you :)

    • @SuperRia33
      @SuperRia33 Месяц назад +1

      I thought I'm the only one who's addicted to sirs videos😅

  • @balrajprajesh6473
    @balrajprajesh6473 2 года назад +4

    why is this channel not having a million subscribers already?

  • @manjushagore904
    @manjushagore904 3 месяца назад

    28:20 ...Pichewali Chhipkaliii ko bhi concept smz aa gya sirrrr😂Itna Perfect kese ho skte ho aap...
    MIND BLOWING Explanation🔥🔥🔥🔥

  • @narendraparmar1631
    @narendraparmar1631 10 месяцев назад +2

    Thanks for this clear explanation.

  • @vankadavathrohith1589
    @vankadavathrohith1589 6 месяцев назад

    Can't explain how ease it become after watching your video. Thank you so much for this playlist.

  • @hossain9410
    @hossain9410 5 месяцев назад

    i did some optimization and got 98.6% accuracy.. Thank u sir for teaching us such wonderful things .

  • @ahsankhans9514
    @ahsankhans9514 11 месяцев назад +2

    I really love your videos.I'm from Pakistan

  • @SHIVAMGUPTA-wb5mw
    @SHIVAMGUPTA-wb5mw 2 месяца назад

    finally getting good understanding on deep learning

  • @shashankshekharsingh9336
    @shashankshekharsingh9336 7 месяцев назад +1

    thank your sir , bing watching your playlist like a netflix series

  • @maharkreviews6942
    @maharkreviews6942 Год назад +3

    i recommend your channel to my every studnt

  • @tejaspote5768
    @tejaspote5768 11 месяцев назад

    00:01 Introducing the famous MNIST dataset for handwritten digit classification.
    02:30 Handwritten digit classification using neural network architecture
    05:26 The video discusses loading the famous MNIST dataset and understanding its structure.
    08:30 Create a neural network architecture for digit classification
    11:16 Setting up layers and architecture for image data in Sequential Model
    14:03 Explanation of model architecture and parameter calculation
    16:51 Discussed label coding and model compilation for training
    19:28 Handwritten digit classification using ANN and the MNIST Dataset
    22:09 Adding another layer and increasing model parameters
    25:09 Using artificial neural network for multi-class classification problem
    27:52 Handwritten digit classification using ANN and MNIST dataset

  • @jayantsharma2267
    @jayantsharma2267 2 года назад +3

    binge watching your entire series
    thanks for the great content,

  • @COCDesiWarriors
    @COCDesiWarriors Год назад +1

    Thank you Sir... Ab jake kafi cheeze clear hue :)

  • @shashankbarai1809
    @shashankbarai1809 28 дней назад

    sir aap feedback ka toh pucha hi mat karo, ur always best. :)

  • @raviabhicreations1967
    @raviabhicreations1967 3 месяца назад

    mind blowing sir it , your teaching method is like makkhan

  • @meetvardoriya2550
    @meetvardoriya2550 2 года назад +9

    Sir BERT aur transformer models 100 days DP vale mein cover karoge ya NLP vale mein

    • @campusx-official
      @campusx-official  2 года назад +8

      Dono me daal denge

    • @harshmohan8419
      @harshmohan8419 2 года назад

      @@campusx-official sir topic nlp kab tak cover hoge.... Usko thode jaldi kardijiye. If possible

  • @vishalk9788
    @vishalk9788 5 месяцев назад

    Hi Nitesh thank you for giving such lucid videos. I have seen other trainings including from Harvard or MIT or other ed tech platforms, but your videos are best to understand. It was your video which made concept of perceptron and MLP literally crystal clear. Thanks a ton sir .
    Alao taking this occasion to say Happy Guru purnima as you are virtual Guru for me in my journey of AI🙏

  • @SushmaMule
    @SushmaMule 5 месяцев назад

    Excellent sir.❤

  • @maharkreviews6942
    @maharkreviews6942 Год назад

    hahhaha hum ny compile ni hum ny complile kia ha. love you i watched your every video .learn alot about deep learning and your big fan

  • @gauravagrawal6768
    @gauravagrawal6768 9 месяцев назад

    very well explained, Nitish it would be great if you could explain how 60000 image input is given to the first layer of ANN after converting to 1 D array, we have 728 pixel in each image, how they are connected to first layer

  • @movietime2613
    @movietime2613 Год назад +3

    Sir you took exactly 128 nodes in hidden layer how to choose to take that?

  • @mohammedameer9909
    @mohammedameer9909 2 года назад +5

    Please mention Day number for every video to keep track

  • @8791692532
    @8791692532 2 года назад +7

    Sir, you ealier said at the start of playlist that we do not need feature engineering in Deep Learning, but we also need feature engineering to get better results in Deep Learning, infact in these two examples you done feature engineering to train Neural Networks. So feature engineering is required in Deep learning?

  • @pbalajipatro6399
    @pbalajipatro6399 Год назад +1

    thank you so much sir making this types of vdo

  • @ShubhamSharma-gs9pt
    @ShubhamSharma-gs9pt 2 года назад +2

    best yt resource for DS!

  • @iqbaljaved8026
    @iqbaljaved8026 8 месяцев назад

    Nice sir, please make videos for deep learning

  • @ShubhamKumar-m7y
    @ShubhamKumar-m7y 6 месяцев назад

    thank you sir for your effort .

  • @ayushparwal2004
    @ayushparwal2004 6 месяцев назад

    nice content sir. really helping

  • @RohitVishwakarma-fz9fp
    @RohitVishwakarma-fz9fp Год назад +1

    @campusx please let me know why we used 128 node in hidden layer

  • @StartGenAI
    @StartGenAI 2 года назад +2

    Great video 🙏

  • @bhavikdudhrejiya852
    @bhavikdudhrejiya852 2 года назад +2

    Very informative video

  • @121_bimandas9
    @121_bimandas9 Год назад +1

    Can we check here any other images except from the mnist data set ??

  • @manavdesai1703
    @manavdesai1703 5 месяцев назад +1

    28:24 Lizard behind Nitish sir😳

  • @englishtalkers1939
    @englishtalkers1939 8 месяцев назад

    sir, i don't want to like and share because everyone will come to know about this masterpiece

    • @shashankshekharsingh9336
      @shashankshekharsingh9336 7 месяцев назад +1

      kya bhai, sir itna mehnat kar rahe aur tum abhi in sab chizo me hi fase ho , recommend it to as many people you can , make this guy popular because he deserves it

  • @aayda330
    @aayda330 Месяц назад

    can anyone tell me how do I get the all the trained weights

  • @rb4754
    @rb4754 6 месяцев назад

    Amazingggggg!!!!!!!!!!!!!!!!!!!!!!!!

  • @rafibasha4145
    @rafibasha4145 2 года назад +1

    13:07,Hi Bro,why you havent used flatten in churn prediction case

    • @yashgourav
      @yashgourav 2 года назад +2

      churn prediction is 1-d array, not 2-d array

  • @Naman_Bansal102
    @Naman_Bansal102 7 месяцев назад

    Wah maza A Gya

  • @sachinsingh1163
    @sachinsingh1163 10 месяцев назад

    very nice bhaiya

  • @minalgupta7456
    @minalgupta7456 7 месяцев назад

    i am big fan of you

  • @Prathamesh__27
    @Prathamesh__27 4 месяца назад

    thank you sir

  • @rajeshjana3541
    @rajeshjana3541 8 месяцев назад

    how I give a dataset of an experiment as a input and process the same whole programme...response please...

  • @AdityaKumar-fq2lq
    @AdityaKumar-fq2lq 2 года назад +4

    can any one explain.. hidden layer mai 128 nodes he kyu hai?

  • @idontknow2iknow905
    @idontknow2iknow905 7 месяцев назад +1

    One small doubt - Why we had to divide by 255 ? Why can't we use Standard Scaler to standardize the data.

  • @raushanpathak2748
    @raushanpathak2748 11 месяцев назад

    why devide by 255 of x_train?

  • @amruth505
    @amruth505 10 месяцев назад

    why does this not work from custom images(28,28) created from paint not predict properly, even after tweking the hyperparameters. i created digits [0,2,4,5,6,8,9] on paint wtih size(28,28). I got 1 out of 7 correctly (at this point it was just random)
    for x in [0,2,3,4,6,8,9]:
    img=cv2.imread(f'data/numbers/{x}.png')[:,:,0]
    img=np.array([img])
    prediction = model.predict(img)
    print(f' result :{np.argmax(prediction)}')
    plt.imshow(img[0])
    plt.show()

  • @LakshyaIIITD
    @LakshyaIIITD 8 месяцев назад

    what if images are MNIST-back-image, how to denoise them ??

  • @social.2184
    @social.2184 7 месяцев назад +1

    Did we assume that the hidden layer will contain 128 nodes or did i miss something?

    • @rahulphatak2909
      @rahulphatak2909 7 месяцев назад +1

      Yes, you are correct. We are only assuming there are 128 nodes.

  • @SundarKotturi
    @SundarKotturi 5 месяцев назад

    how can i create a hand digit data..

  • @dipanshupandey7952
    @dipanshupandey7952 2 года назад

    easy to understand

  • @pritishbanerjee5517
    @pritishbanerjee5517 Год назад

    Thanks for all your sessions. Do you plan to start a paid batch for Deep Learning in near future similar to the lines of Machine Learning batch ?

  • @fozler
    @fozler 2 года назад +1

    Hello sir, please make an video about validation_split. I have doubt about this

  • @healinghope7080
    @healinghope7080 Год назад

    Where 255 coming from? 10:13

  • @asfarali225
    @asfarali225 Год назад +1

    Sir kindly make a tutorials streamlit python

  • @anuj7876
    @anuj7876 Год назад

    What about the color image digit recognition it will have 3 different RGB value unlike black and white all same value

  • @sourabhshashidhar6461
    @sourabhshashidhar6461 2 года назад

    Amazing sir😄

  • @shaiksalavuddin5976
    @shaiksalavuddin5976 2 года назад +2

    Sir what about back propagation

  • @AnandTiwariJDE
    @AnandTiwariJDE 9 месяцев назад

    great videos. The playlist says 100 days, but there are only 76 videos. Does it cover all the topics or am I missing any video (i have not watched all the videos just want to make sure that I am referring the correct playlist or not) Appreciate if someone or CampusX can provide inputs

    • @Tusharchitrakar
      @Tusharchitrakar 8 месяцев назад +2

      The video list is still not complete. He's still in the process of finishing it. So don't worry: 100 days is just an approximate number and it's currently ongoing

  • @Sara-fp1zw
    @Sara-fp1zw 2 года назад +1

    Shukria

  • @arshad1781
    @arshad1781 2 года назад +1

    Thanks 🙏

  • @rohitrai9579
    @rohitrai9579 2 года назад

    sir, model. predict(X_test) is giving us prob,but when I see the array its value is greater than 1 so how is argmax converting to digit?

  • @dilipgyawali1776
    @dilipgyawali1776 2 года назад +1

    why the image is colorful??as u are saying the image is in the range of 0 to 255

  • @vijaysingh-bw2fk
    @vijaysingh-bw2fk Год назад

    Namaste guruji, i trained my model and applied StandardScalar, somehow managed to make changes on model and now it gives 99.15% accuracy, now i want to test it on real world data, so should i reconvert new data to standard form or use serialisation? Using pickle is not good because if i update model or preprocessing pipeline, the pickled files might become outdated. Any suggestions how to do it seamlessly? Your useful insights and suggestions will be highly solicited. Thanking you in advance and await your reply.

  • @mrityunjayupadhyay7332
    @mrityunjayupadhyay7332 Год назад

    Amazing

  • @aninditasaha0307
    @aninditasaha0307 2 года назад +1

    Hidden layer me 128 nodes kyun liya?

    • @javaria_Ibrahim
      @javaria_Ibrahim Год назад

      Bcz ye compulsory nh hai ap jitnen b leskty ho

  • @alfejmansuri9795
    @alfejmansuri9795 5 дней назад

    Why we just took a prediction that the index with highest probability is the number, I mean why is it true what if our 3rd node is predicting for 8, or any i node predicts for a j value?

  • @jitendramishra7464
    @jitendramishra7464 2 года назад +3

    First Viewer and Liker

  • @zkhan2023
    @zkhan2023 2 года назад +1

    Thanks sir

  • @sandipansarkar9211
    @sandipansarkar9211 2 года назад

    finished watching

  • @paragvachhani4643
    @paragvachhani4643 2 года назад

    To run model and all ...deep learning is easy thae ML..
    am i think right ..? (With keep in mind diffrence between ml and deep learning model)

  • @yashjain6372
    @yashjain6372 Год назад

    best

  • @aviralsoni141
    @aviralsoni141 Месяц назад

    you are doing the practical part before the theorey, that's why it is a bit difficult to understand, also the code section is also tricky.

  • @rahulsuryawanshi3960
    @rahulsuryawanshi3960 Год назад

    Thanks

  • @sheershsaxena9357
    @sheershsaxena9357 7 месяцев назад

    WHY 128 NODES IN THE FIRST HIDDEN LAYER????

    • @rahulphatak2909
      @rahulphatak2909 7 месяцев назад

      You can select any number of nodes

  • @illusions8101
    @illusions8101 Год назад

    Thanks you sorrrr

  • @mathanimation7563
    @mathanimation7563 2 года назад +1

    can we do the same project without using any extra library if yes then please make a video

  • @sharadpkumar
    @sharadpkumar 4 месяца назад

  • @ArpanChandra-vv8cg
    @ArpanChandra-vv8cg 3 месяца назад

    can anyone talking a proper notes !? If yes then share with me please 🙏🏻

  • @namyashah3173
    @namyashah3173 4 месяца назад

    you seem to be a brother of @krish naik 😅🤣

  • @vishnujatav6329
    @vishnujatav6329 2 года назад +1

    Achcha hai but jyada samajh me nhi aa rha hai Nitish

    • @campusx-official
      @campusx-official  2 года назад +1

      nitish.campusx@gmail.com ek baar ispe explain karoge issue?

  • @sandipansarkar9211
    @sandipansarkar9211 2 года назад

    finished coding

  • @elonmusk4267
    @elonmusk4267 6 месяцев назад

    hooray

  • @devicedevice-k8o
    @devicedevice-k8o Год назад

    speak english sir

  • @tanmayshinde7853
    @tanmayshinde7853 2 года назад +2

    Sir, your efforts have to be appreciated cause you wake up early in the morning and make videos for us. Thank You, Thank You So Much!