CS231n Winter 2016: Lecture 2: Data-driven approach, kNN, Linear Classification 1

แชร์
ฝัง
  • เผยแพร่เมื่อ 17 ธ.ค. 2024

ความคิดเห็น • 73

  • @susdoge3767
    @susdoge3767 6 หลายเดือนก่อน +12

    andrej has the most unique way of telling things and generally they are more intuitive, what a maniac!

    • @anon-yn9rc
      @anon-yn9rc 6 หลายเดือนก่อน

      yeah completely agree he is just excellent!

  • @leixun
    @leixun 4 ปีที่แล้ว +66

    *My takeaways:*
    *1. Why image classification is hard **3:00*
    *2. Data-driven approach is more scalable than hand-crafted approach **6:48*
    *3. Nearest Neighbor classifier **9:11**: remember all training images, and comparing test image with every single one of them; transfer the label from the training image (that is most similar to the test image) to the test image*
    3.1 How to measure similarity? 10:51: L1 distance (Manhatten distance)
    3.2 Classification speed depends on the size of the training data 12:50
    3.3 Speed up classification 14:06
    3.4 How to measure similarity? 14:23: L2 distance (Euclidean distance)
    3.5 The choice of distance is a hyperparameter 15:00
    *4. k-Nearest Neighbor **15:17**: similar to Nearest Neighbor classifier, but instead of finding the most similar training image, kNN finds k most similar images, and has them to vote on the label*
    4.1 Distance and k are both hyperparameters 18:33, we have to try different values to see what works best
    4.2 Training/validation/test data, and cross-validation 18:56
    4.3 kNN on images never used 24:00
    4.4 Summary 25:20
    *5. Linear classification **25:59*
    5.1 Parametric approach 29:47
    5.2 Linear classifier 31:21
    5.3 Interpreting a liner classifier 40:01
    5.4 What would be a very hard test dataset for liner classifier? 47:33
    5.5 The needs for a loss function 52:25

  • @anant8884
    @anant8884 5 ปีที่แล้ว +40

    some questions students asked were exceptionally good...

  • @pauldacus4590
    @pauldacus4590 6 ปีที่แล้ว +15

    32:25 Probably the first coherent explanation I've heard about what "bias" actually represents.

  • @abc3631
    @abc3631 4 ปีที่แล้ว +25

    Thank god for making cats, they seems to be essential to understanding ML

  • @WorldMusicCafe
    @WorldMusicCafe 9 ปีที่แล้ว +60

    I was around 12 when I used to watch your speedcubing videos and got into sub-20s. I am now 20 and watching your CNN videos. Your explanation style like before, is extremely lucid.
    Time flies so fast! Welcome back to TH-cam, Mr. Badmephisto.

    • @mrtamborineman10
      @mrtamborineman10 8 ปีที่แล้ว +1

      +World Music Cafe Is this really Badmephisto?? I never connected the dots but I used to watch him and knew that he was going to stanford

    • @WorldMusicCafe
      @WorldMusicCafe 8 ปีที่แล้ว +2

      Yup, he is Badmephisto. I knew it early that his name was Andrej, but I never knew that he is going to be this famous. He is smart, after all.

    • @mynameajeff7459
      @mynameajeff7459 5 ปีที่แล้ว +1

      Wow, I used to watch his speedcubing videos too and now I am here watching his CNN videos.

    • @tyfoodsforthought
      @tyfoodsforthought 4 ปีที่แล้ว +3

      Haha, this thread is so cool.

    • @SharatS
      @SharatS 2 ปีที่แล้ว

      Me too... He was the OG cubing TH-camr.

  • @wlorenz65
    @wlorenz65 8 ปีที่แล้ว +12

    What happened there at 15:00 is called "Dropout", and it's also a regularization technique like L1 and L2.

  • @adityapasari2548
    @adityapasari2548 7 ปีที่แล้ว +4

    After watching so many MOOC's , this is the first class I saw where students are asking so many questions. Just an observation.

  • @gyxlucy
    @gyxlucy 9 ปีที่แล้ว +3

    really like the part of interpreting simple models in various ways :) looking forward for more such intuitive interpretations for more complicated networks

  • @gauravsavlani7644
    @gauravsavlani7644 7 ปีที่แล้ว +6

    Terrific explanation. One hell of a faculty

    • @JesusMartinoza
      @JesusMartinoza 4 ปีที่แล้ว +1

      I know! I want to study there so bad!

  • @double_j3867
    @double_j3867 7 ปีที่แล้ว +7

    You're a very good lecturer keep it up. I'll be looking for more online courses from you buddy.

  • @wifi-YT
    @wifi-YT 4 ปีที่แล้ว +2

    At 22:22, a student asks if the reason the larger K values lead to poorer accuracy is due to high bias (i.e., underfitting), and the instructor says he can’t say that for sure. But it seems to me the student was correct: that a too high K value leads to underfitting, at least as to that particular dataset. (Conversely, a too low K value leads to overfitting). Anyone agree?

    • @GohOnLeeds
      @GohOnLeeds ปีที่แล้ว

      Andrej actually said "I would be careful with that terminology."

    • @wifi-YT
      @wifi-YT ปีที่แล้ว

      @@GohOnLeedsBut he concluded with “It’s basically hard to say.” 22:41

  • @sayhongtan8993
    @sayhongtan8993 9 ปีที่แล้ว +6

    Great explanation! Wish my prof was as good as explaining as you are!

  • @Sauskethorpido
    @Sauskethorpido 9 ปีที่แล้ว +3

    thanks a lot, it will be great of there can be MOOC for this course

  • @ujjwaljain2196
    @ujjwaljain2196 7 ปีที่แล้ว +1

    It'll be very good if we can get all the links displayed in the class in the description below.

  • @demoticshadow2494
    @demoticshadow2494 3 ปีที่แล้ว +1

    What would be a good approach to gray scale? For example a radiograph looking for a know defect?

  • @mohamedtarek8899
    @mohamedtarek8899 4 ปีที่แล้ว

    in 33:33 why W equal (3, 4), I know that we have 3 classes but there is just one example which output must be (1, 1). so what if I have 200 example , 20 classes and 1000 nx, should w be (20, 200, 1000) ?

  • @CorporateDrone
    @CorporateDrone 2 ปีที่แล้ว

    Lecture starts at 3:03

  • @jacobthorn2800
    @jacobthorn2800 7 ปีที่แล้ว +2

    What happened at 51:13?

  • @kaustubhvijayjoshi
    @kaustubhvijayjoshi 9 ปีที่แล้ว +1

    thanks for uploading videos. great work.please keep it up

  • @MrPandachencheng
    @MrPandachencheng 8 ปีที่แล้ว +3

    why does translation of object position in the image would not have large effects on the linear classifiers?

    • @YaSerhiy
      @YaSerhiy 8 ปีที่แล้ว

      AFAIK, it does have huge effect on the performance of the linear classifier.

    • @AndreLami
      @AndreLami 5 ปีที่แล้ว

      To clarify, he says about situation when dog in the center is one class, and in the corner is different class. Then it is not a problem for linear classifier, it can update weights the way to distinguish these classes, that differ by position (image can be the same, but position defines class)

  • @shubhstiws
    @shubhstiws 2 ปีที่แล้ว

    I do not understand the images which would be hard to classify by a linear classifier, and also interpreting a linear classifier in a high dimensional space.
    How is the classifier drawing boundaries around clusters of 'dog' images when projected into the high dimensional space.
    I imagined the images as 3x1 pixel images and projected into the 3D space. Multiple images can be plotted here and lets say the images with high brightness in pixel 2 gets clustered on the y axis with different x and z variables, now a 2D plane (xz) can be drawn separating the area above and below these brightness clumps, which can be treated as a separation boundary. Is this interpretation correct ?

  • @bennychan6263
    @bennychan6263 7 ปีที่แล้ว +1

    Q: What does the linear classifier do, in English?
    A: Create a dart board with N high score areas. When you throw a new dart, it will tell your dart is an airplane.

  • @vq8gef32
    @vq8gef32 8 หลายเดือนก่อน

    Amazing Course ! Thank you!

  • @ThienPham-hv8kx
    @ThienPham-hv8kx 3 ปีที่แล้ว

    I summarized his awesome lecture: we tried to comprehend linear function in linear classification: f(x)=ax+b (more detail at: en.wikipedia.org/wiki/Linear_function).
    Linear classification is starting point toward convolution neural network (CNN). In my opinion, linear classification 's in 1 word is "trend" , if it 's in full explanation : this is line of railway that will take all objects near or inside it a label or the name of object.

  • @gurujicoder
    @gurujicoder 2 ปีที่แล้ว

    47:40 same colors but different objects like ship and car of same color and sky and ocean

    • @gurujicoder
      @gurujicoder 2 ปีที่แล้ว

      also quadratic or circular distinctions

  • @lynnsamson2915
    @lynnsamson2915 6 ปีที่แล้ว

    How is the L2 distance the same between the original and distorted images? Wouldn't the distortion lead to a non-zero difference in the pixel values, making them different?

  • @gxhoi
    @gxhoi 5 ปีที่แล้ว

    hello i'm here to feel how fast he is. from comments of Deep rl bootcamp 3rd lecture. wow. its was real.

  • @tianshuyang121
    @tianshuyang121 7 ปีที่แล้ว +3

    One of the questions that Would it be problem if image at centre or image at the right? I guess the answer is No, i.e the linear classifier would handle that but I'm not sure it's correct

    • @AndreLami
      @AndreLami 5 ปีที่แล้ว +2

      To clarify, he says about situation when dog in the center is one class, and in the corner is different class. Then it is not a problem for linear classifier, it can update weights the way to distinguish these classes, that differ by position (image can be the same, but position defines class)

  • @danieldefreitas148
    @danieldefreitas148 9 ปีที่แล้ว +1

    Great stuff. Just FYI in case you didn't notice: the video resolution is a bit low (360p). The video for the first lecture was available in up to 1080p which is sometimes helpful for reading small details. Thanks a lot anyway.

    • @alberthaque8461
      @alberthaque8461 9 ปีที่แล้ว +8

      +Daniel de Freitas Adiwardana The original video is recorded at 1080p. It takes TH-cam a few hours to fully process it (which is why it starts at 360p)

  • @JoyJulianGomes
    @JoyJulianGomes 7 ปีที่แล้ว

    in linear classifier what does the images in training set do if we select the W matrix randomly?

  • @ankursatya4733
    @ankursatya4733 7 ปีที่แล้ว +1

    How are templates for classes made?

  • @AllanZelener
    @AllanZelener 9 ปีที่แล้ว

    Nice to have videos this time, I'm looking forward to more. One nitpick, you referred to a linear classifier as "parametric" and nearest neighbor as "nonparametric" but these terms seem to have a different meaning in statistics. Parametric refers to parameterized probability distributions, e.g. the normal distribution is defined by the mean and variance parameters. In this sense, even if we have a neural network approximating a normal distribution the model would be nonparametric since it wouldn't explicitly use the mean and variance parameters. To avoid this confusion, even though it's a mouthful, I prefer the term "parameterizable" to distinguish models that do and don't use any parameters.

  • @hanqiu4386
    @hanqiu4386 8 ปีที่แล้ว

    Thanks for the awesome videos!

  • @bingeltube
    @bingeltube 6 ปีที่แล้ว +1

    Recommendable, but a bit to trivial

  • @gaussic6985
    @gaussic6985 7 ปีที่แล้ว +14

    0.75 speed is good for me.

    • @JousefM
      @JousefM 4 ปีที่แล้ว

      WOW. You are really living on the edge here. I would go with 0.25 :D ;)

  • @mheitm
    @mheitm 4 ปีที่แล้ว

    On slide 51 at 33:12 the ship score is incorrect for the numbers shown. It should be 60.75, the value of 61.95 comes from calculating with the last ship weight as 0.3, and not -0.3.

  • @cavallonechen8349
    @cavallonechen8349 7 ปีที่แล้ว

    He is so smart.

  • @kushalkanungo9749
    @kushalkanungo9749 7 ปีที่แล้ว

    Can anybody explain how vornai tessalation changes with k in k-nn? Or how to get decision boundaries for k-nn??

  • @enestemel9490
    @enestemel9490 6 หลายเดือนก่อน

    Very good lecture, Andrej. Also, the student who interrupted Andrej by saying 'that was what I said' didn't have a good tone and annoyed me.

  • @lilyzhao5397
    @lilyzhao5397 7 ปีที่แล้ว

    How could people in Chinese area load vitual machine and assignment link?Thanks.

  • @aleksandarabas6618
    @aleksandarabas6618 2 ปีที่แล้ว

    My teacher

    • @aleksandarabas6618
      @aleksandarabas6618 2 ปีที่แล้ว

      watched the lectures in the hotel room at lake tahoe

    • @aleksandarabas6618
      @aleksandarabas6618 2 ปีที่แล้ว

      before that everything I know can be easily traced to IOI and that gap year I spent in Bulgaria 2015-2016

  • @ONeilPoppy-l1k
    @ONeilPoppy-l1k 3 หลายเดือนก่อน

    Garcia Elizabeth Clark Mark Wilson Brian

  • @miji3834
    @miji3834 7 ปีที่แล้ว

    这集的中文翻译不如lecture 1

  • @teimoorbahrami8634
    @teimoorbahrami8634 5 ปีที่แล้ว

    cannot understand the machine learning :((((((((((

  • @abhishekkumar-os5zk
    @abhishekkumar-os5zk 4 ปีที่แล้ว +3

    So prof does not know how to fix projector but know ai.

  • @JayJay-zh6ei
    @JayJay-zh6ei 7 ปีที่แล้ว +1

    Who else thinks that he reminds you of Justin Timberlake....?

  • @kasperwynne154
    @kasperwynne154 7 ปีที่แล้ว

    I believe the Chinese subtitle is translated by machine. Total disaster :(
    And he talks so fast its really hard to catch up.
    Good lecture though.

  • @huynhhuynguyen9025
    @huynhhuynguyen9025 9 ปีที่แล้ว +7

    He talk so fast compared with prof. Li fei fei. Why prof.Li FF don't continue teaching cs231n??

    • @KhueLe
      @KhueLe 9 ปีที่แล้ว +3

      +huynh huy nguyen I believe Andrej has always been the main instructor. Click on the CC button for the subtitles.

    • @MarkTrovinger
      @MarkTrovinger 9 ปีที่แล้ว +4

      +huynh huy nguyen She mentions in the lecture 1 video that is going to have a baby sometime in the coming weeks.

    • @NeigeFraiche
      @NeigeFraiche 8 ปีที่แล้ว +4

      +huynh huy nguyen You can adjust the speed with the little gear icon on the bottom of the video

    • @ThienPham-hv8kx
      @ThienPham-hv8kx 3 ปีที่แล้ว

      @@NeigeFraiche Thank you

  • @woooooooo-r9o
    @woooooooo-r9o 4 ปีที่แล้ว

    中文翻译太差劲了