Deep Learning(CS7015): Lec 2.5 Perceptron Learning Algorithm

แชร์
ฝัง
  • เผยแพร่เมื่อ 27 ธ.ค. 2024

ความคิดเห็น • 63

  • @crackbreak1
    @crackbreak1 4 ปีที่แล้ว +33

    I wished other NTPL courses had you as the instructor.

  • @RakeshGupta-ft6cc
    @RakeshGupta-ft6cc 4 ปีที่แล้ว +11

    seriously, his method of teaching is excellent

  • @TheSocialDrone
    @TheSocialDrone 4 ปีที่แล้ว +10

    Loved the way the subject is explained! Hats off!!!

  • @ashishmulchandani8768
    @ashishmulchandani8768 4 ปีที่แล้ว +6

    Great! Understood the whole concept in 10 mins

  • @sidddddddddddddd
    @sidddddddddddddd 3 ปีที่แล้ว +8

    Mathematically, at 4:19, the w and x vectors have been written incorrectly. Basically, vectors are always written as columns and covectors are written as rows. And dot product can be understood as a covector eating a vector and spitting out a real number. Therefore, at 4:19, there should be a transpose on the row vectors if he wants to write it like that.

    • @sachinsinghchauhan9861
      @sachinsinghchauhan9861 3 ปีที่แล้ว

      Hey can you suggest some links to study basics of vectors, so that there is not any problem in understanding deep learning algorithms?

    • @user-se2pl5hd5s
      @user-se2pl5hd5s 3 ปีที่แล้ว +2

      @@sachinsinghchauhan9861 3 blue 1 brown search it up

  • @sanketmishra7909
    @sanketmishra7909 3 ปีที่แล้ว +1

    How interesting is it..! amazing communication skill

  • @himanshubhusanrath212
    @himanshubhusanrath212 4 ปีที่แล้ว +2

    Very nice explanation Sir.. especially the change of W which you explained by considering each positive and negative point.

  • @mdabubakar6874
    @mdabubakar6874 3 ปีที่แล้ว +10

    it seems students r there just to revise the topics.....

  • @ankitgupta8797
    @ankitgupta8797 3 ปีที่แล้ว

    5:39 every point on the line is perpendicular to w. But what is the direction of such points on the line?

  • @farooq8fox
    @farooq8fox 3 ปีที่แล้ว +2

    So many post production staff and cannot add a fade out and fade in to the vid and audio ?
    The outro is scaring me when i'm on headphones 13:02

    • @shubhamide
      @shubhamide 3 ปีที่แล้ว

      dekho yaar baat aisi hai mujhe computer science mein kuch nahi ata lekin main neural network seekhna chahta hun to isko seekhne ke liye kya kya ana chahiye?

    • @farooq8fox
      @farooq8fox 3 ปีที่แล้ว +1

      @@shubhamide 12thclass/undergrad level - Linear algebra, Matrices, Calculus, Statistics and Probability.
      Some basic programming. Inke bina dimag kharab hoga

    • @shubhamide
      @shubhamide 3 ปีที่แล้ว

      @@farooq8fox maths to ata h ye batao programming ke liye koi source batao

    • @farooq8fox
      @farooq8fox 3 ปีที่แล้ว

      @@shubhamide basic Python programming, and then ek machine learning ka course karlo, preferably the one by Andrew Ng, then you will understand better

  • @TheBala7123
    @TheBala7123 5 ปีที่แล้ว +1

    Could somebody kindly share the pre-requisites for this lecture that the professor is mentioning at 4:18 ?

    • @sanketneema286
      @sanketneema286 5 ปีที่แล้ว

      Linear algebra ,

    • @arnavsingh0
      @arnavsingh0 5 ปีที่แล้ว +2

      @@ayushshukla9070and a little respect for those who want to learn.

    • @AnsumanSingh1
      @AnsumanSingh1 4 ปีที่แล้ว

      th-cam.com/video/LyGKycYT2v0/w-d-xo.html

    • @pranavsawant1439
      @pranavsawant1439 4 ปีที่แล้ว +1

      The site below mentions the prerequisites for the entire course along with the relevant links to access the content
      www.cse.iitm.ac.in/~miteshk/CS7015.html
      Hope this helps!

    • @akashkumbar5621
      @akashkumbar5621 ปีที่แล้ว

      @@pranavsawant1439 this guy is in IITM, but why does the course say IIT Ropar?

  • @saptarshisanyal6738
    @saptarshisanyal6738 5 หลายเดือนก่อน

    Why are we not considering the loss while updating the weights here? Why are we summing up or subtracting the input vector from the weight vector?

  • @ajayrana4296
    @ajayrana4296 3 ปีที่แล้ว +4

    content and topics is far better than others but everything is going fast not in detail ... so hard to understand

  • @dailyDesi_abhrant
    @dailyDesi_abhrant 4 ปีที่แล้ว +3

    Why are we doing w+x and w-x ? /We can add any vector to w in the direction of x right? Why 'x' precisely?

    • @abhirupbhattacharya3373
      @abhirupbhattacharya3373 4 ปีที่แล้ว +1

      to correctly set the value of W. this is done during training to set the optimum value of W when inputs are X in n+1 dimensional space

    • @sachinsinghchauhan9861
      @sachinsinghchauhan9861 3 ปีที่แล้ว

      @@abhirupbhattacharya3373 hey bro! Can u suggest me some basic materials to study concepts of vectors? I don’t understand vectors and that’s why i always feel trouble in studying deep learning concepts.

  • @sindijagrisle6551
    @sindijagrisle6551 5 หลายเดือนก่อน

    at 8 minutes, it works not only by given explanation but also it comes from epoch training formulas : a) Y2^(i)=beta(x^|I|t *W) b) err=y^|I|-Y2^|I| ...(true-prediction) c) w=w+err*X|I|... depending on error the equation is gonna change, if error is -1 then from the c) equation we can see thhen=w-X^i. It basically means if the predicted output(Y2) is =0 and target(Y) is 1, then we need to=x+w, what graphically would mean that line dividing classes would go to the left side from class 1 to class 0. And opposite can happen: if output is 1, target 0, then need to subtract input vector from weights. It is something to deal with errors and its not understandable from this clearly.

  • @bavidlynx3409
    @bavidlynx3409 2 ปีที่แล้ว

    thank god you mentiuoned that x'x is a positive quantity thats why cos alpha is < or > in respective cases at 9:14. i was starting to get really worried

  • @SuperVarunsharma
    @SuperVarunsharma 3 ปีที่แล้ว +1

    Same problem. Indian institutions have this perception that everyone knows everything. He did not bother to explain many things.

    • @farooq8fox
      @farooq8fox 3 ปีที่แล้ว +1

      This is a university level course and linear algebra, calculus are prerequisites for this. But yea he should've mentioned them for the sake of online audience

    • @shubhamide
      @shubhamide 3 ปีที่แล้ว

      @@farooq8fox bhai calculus aur linear algebra to ata h lekin ye "while do" kya cheez hai?

    • @siddharthmagadum16
      @siddharthmagadum16 3 ปีที่แล้ว +1

      @@shubhamide It's a loop, in programming pseudo code language. google while loops.

  • @anand3064
    @anand3064 2 ปีที่แล้ว

    Just wow!!

  • @krishnachauhan2850
    @krishnachauhan2850 2 ปีที่แล้ว

    what is the error at 9.27?

  • @souhardyahalder3903
    @souhardyahalder3903 6 หลายเดือนก่อน

    can anyone explain how point p1 , p2 ,p3 , n1 are greater than 90

  • @himanshumangoli6708
    @himanshumangoli6708 2 ปีที่แล้ว

    Algorithm will surely converge but some of the training points whether positive and negative it will make errors because we never get 100℅ accuracy score even on training data if somehow we achieved it our system or model get overfitted

  • @nitindia5068
    @nitindia5068 10 หลายเดือนก่อน

    Can anyone explain this please, How at 10.10 he is assuming angle between p1 and initial w is greater than 90? I mean how the angle is measured? I believe between w and pi right? I cant figure it out how is it seems to be greater than 90 seeing this figure. and this happens again after modifying w between new w and p2. Please explain.

    • @anonymous9217w2
      @anonymous9217w2 10 หลายเดือนก่อน +1

      lol you are so dumb

  • @afghaniiit5627
    @afghaniiit5627 4 ปีที่แล้ว

    at @8:40
    cos(alpha_new) > cos(alpha)
    => alpha_new < alpha

  • @saisri1000
    @saisri1000 4 ปีที่แล้ว +3

    Why are we doing w=w+x and w=w-x can anyone please explain how did we get this?

    • @sahilaseeja7686
      @sahilaseeja7686 4 ปีที่แล้ว +1

      See this is done in order to find the line between linear separable data. Look w is selected randomly. So now we select x which is any of the points so if the x is a positive point the we computed w.x and if w.x

    • @arvind31459
      @arvind31459 4 ปีที่แล้ว +2

      Take a cosine distance formula i.e, (w^t x) / (||w|| ||x||), if we add x to w (w=w+x) => w^t x increases => cosine distance increased. When does cosine distance increase? Only when angle θ decreases between two vectors. So to make correct predictions for every error,(a +ve point is predicted as -ve) we add x or subtract (a -ve point is predicted as +ve) x from w accordingly. Weights and biases are randomly initialized (by using Glorot initializers, He initializers etc.)in neural networks and are only trainable parameters in whole of DNN.

  • @himanshiswaroop9549
    @himanshiswaroop9549 5 ปีที่แล้ว

    Should the x vector be a unit vector as if we add XtX to WtX it should be such that cos(anew) should not exceed 1

    • @RahulMadhavan
      @RahulMadhavan 4 ปีที่แล้ว +1

      not needed. Norm of weight (w) is in denominator.

  • @reactor2208
    @reactor2208 5 ปีที่แล้ว +1

    Great

  • @ankitbillore8221
    @ankitbillore8221 5 ปีที่แล้ว +1

    can anybody please explain me, why we add w = w+x, and w=w-x??????

    • @arvind31459
      @arvind31459 4 ปีที่แล้ว +3

      I'm sure you must have got the answer by now but I'm just answering if anyone in future has the same doubt.
      Take a cosine distance formula i.e, (w^t x) / (||w|| ||x||), if we add x to w (w=w+x) => w^t x increases => cosine distance increased. When does cosine distance increase? Only when angle θ decreases between two vectors. So to make correct predictions for every error, in this case a +ve point is predicted as -ve, we add or subtract (a -ve point is predicted as +ve) x from w accordingly.

    • @shubhamide
      @shubhamide 3 ปีที่แล้ว

      @@arvind31459 bhai cosine distance kya cheez hoti hai..aur iska iss cousre se kya lena dena h?

  • @sohambasu660
    @sohambasu660 3 ปีที่แล้ว

    I have 1 question:
    why are we considering x0 = 1 ? because we are writing the equation as summation ( 0 to n) (w(i)x(i))

    • @umang9997
      @umang9997 ปีที่แล้ว

      See previous video regarding MP Neurons.

  • @louerleseigneur4532
    @louerleseigneur4532 4 ปีที่แล้ว +1

    merci

  • @upnrunning4585
    @upnrunning4585 4 ปีที่แล้ว

    we can apply gradient descent?

    • @sahilaseeja7686
      @sahilaseeja7686 4 ปีที่แล้ว

      Yeah you can.. but earlier when perceptron paper was presented, this was using this way only. But later on gradient descent method was also discovered in relation to this.

    • @ashiqhussainkumar1391
      @ashiqhussainkumar1391 4 ปีที่แล้ว

      Bro plz tell me what python libraries are used in the course.. Tenserflow or pytorch or anything else.. Then I'll start working on them

  • @abhisheklohia
    @abhisheklohia 4 ปีที่แล้ว

    can anyone explain how Cos(A new) > Cos(A) , but (A new) < (A old) 8:18

    • @akashchandra9338
      @akashchandra9338 4 ปีที่แล้ว +1

      cos A is a decreasing function from 0-90 degrees

    • @jimmymathew8540
      @jimmymathew8540 4 ปีที่แล้ว

      Assume cos A = 0, then A = cos^-1 (0)= 90 deg
      Now increasing the value of cos A, ie, cos A = 0+0.1 = 0.1 , ie, cos(A new) = 0.1 and A new = cos^-1 (0.1) = 84.2 deg
      When value of cos A increase the angle it represents decreases.
      So from the above explanation we can reach a conclusion that when cos(A new) > cos(A) -> A new < A
      Hope it helps

  • @vineetsingh4076
    @vineetsingh4076 5 ปีที่แล้ว

    At 1:40 what does he mean by saying positive and negative input? As in the previous slide, he clearly mentioned that either input is binary or between 1 and 0.
    Really a poor quality from NPTEL

    • @dummy_ani
      @dummy_ani 5 ปีที่แล้ว +6

      By positive input he means inputs having a positive output.

    • @sidddddddddddddd
      @sidddddddddddddd 3 ปีที่แล้ว +1

      He clearly defines the positive and negative input at 1:38. Positive inputs are the ones which give output (i.e. label) 1 and negative inputs are the ones which give the output 0. Why just 0 and 1? Because it is a binary classification problem we are referring to. And even if you will google, you will see that the Perceptron algorithm is a two-class (binary) classification machine learning algorithm.
      eg. We have two possible output in the example that he has considered. So, the labels will be:
      Liked the movie = 1
      Not liked the movie = 0

  • @ranarana-sp7um
    @ranarana-sp7um 4 ปีที่แล้ว +5

    poor fellow..never seen any waste lecture from nptel..he assuming all other knows everything