The Neural Network, A Visual Introduction

No video

The Neural Network, A Visual Introduction

Рет қаралды 143,384

vcubingx

Күн бұрын

Пікірлер: 275

@vcubingx 2 жыл бұрын

Part 2 is out! kzfaq.info/get/bejne/Y8ekarZ91Lyvj30.html

@Mehrdadkh87 Жыл бұрын

We are looking for Part 3. Thx for sharing your experience and knowledge.

@unoriginalusernameno999 4 жыл бұрын

Did you just say you got Yann Lecun to help you!!!! He's got a TURING award boi!

@vijayabhaskar-j 4 жыл бұрын

Well, I think he is one of Yann's students so yeah.

@vcubingx 4 жыл бұрын

Haha yeah, Yann was one of the guys who took a look at the video before I published :)

@unoriginalusernameno999 4 жыл бұрын

vcubingx dudeee that is so coolll....

@PrometheusCoding 3 жыл бұрын

Dang

@pinchikassandra 2 жыл бұрын

@@vcubingx that's amazing man!

@nirbhay.8400k 3 жыл бұрын

This Deep Learning Series will be a life-saver for many !

@alexandrepv 4 жыл бұрын

I always tried to visualise the decision hyperplane on the data's domain, but this has been very insightful: Visualising the data into the projected-non-linear domain. Brilliant video! :)

@vcubingx 4 жыл бұрын

Thanks!

@shivChitinous 4 жыл бұрын

This is great! Makes the analogy with biological neurons crystal clear for me for the first time 😄

@vcubingx 4 жыл бұрын

Thanks! I'm happy that you understood it!

@aaronchan6447 4 жыл бұрын

This is actually so good! You've explained it so very clearly and left no gaps in the logic. I have been wanting to get into machine learning, and you have helped immensely.

@mansfiem 4 жыл бұрын

Great stuff! I'm familiar enough to understand the basics, but I love that this is visually done.

@vcubingx 4 жыл бұрын

Glad you liked it!

@charlsssoooo 4 жыл бұрын

I love these videos. All of my life I was considered mathematically stupid. I can't read mathematical notations well. I failed pre-calc. But now as an adult, watching these visual videos have led me to be able to understand those concepts that were impenetrable to me when I was younger.

@tonywang4431 4 жыл бұрын

When you first showed 10:32, I was thinking that ReLUs are very bad because they collapse data too much and makes points indistinguishable. However, you later showed the 3D case in 11:49, which was very insightful for me. When data lies on a low dimensional manifold of a high dimensional space, the 11:49 picture is probably more accurate. In this case, ReLUs don't actually collapse data in such a bad way.

@postvideo97 4 жыл бұрын

ReLUs don't "need" to collapse data, it only collapses what is necessary. If you think in terms of linear combination of functions, 2 ReLUs can be combined into a "S" shaped sigmoid function, and 4 ReLUs can be combined to form a "Bell Curve" function. Both are very crude and merely approximations, but as you increase the number of dimensions they become smoother. An infinite amount of ReLUs (differently scaled and translated) can approximate any function.

@rohanshetty1016 4 жыл бұрын

This is awesome!. I had half-baked knowledge on all these topics before, after watching this video it's crystal clear!. You made it look so simple. Thank You!

@brendawilliams8062 3 жыл бұрын

I liked it too. I couldn’t help notice the accordion action assiciated with the squares roots being used with two lengths to scale them.

@alecunico 4 жыл бұрын

Great man, thank you so much! Can't wait to see the chapter 2!

@FedeGianca 4 жыл бұрын

This is great work from you, congratulations!! Also a big thank you to Grant Sanderson, from @3blue1brown, for manim. Both of you make quality education so much more fun, as it should be. So thanks a lot!

@suleimansiddiqui2468 3 жыл бұрын

Eagerly waiting for chapter 2

@PowerhouseCell 4 жыл бұрын

Really well done! It's cool to see the differences in the way you covered things compared to 3b1b. Can't wait to see more :D

@vcubingx 4 жыл бұрын

Thanks a ton!

@saidelcielo4916 Жыл бұрын

WOW. I've been studying neural networks for a bit now, but this made me see them in a new way. PLEASE MAKE MORE VIDEOS!!!!

@aidosmaulsharif9570 4 жыл бұрын

Man it is just so high level. Your explanation, vizuals and the topic itself are great. Subscribed and waiting for the next chapters!!!

@vcubingx 4 жыл бұрын

Thank you very much!

@TheNostradE3 4 жыл бұрын

Really good content, one of the clearest explanations i've heard about neural networks so far! Keep up the good job, cannot wait for the following videos!

@jamilahmed2926 2 жыл бұрын

By far the most essential visualization of neural net Ive seen to date! 🤩

@ragha1988 4 жыл бұрын

Amazing visualization. Looking forward to next videos in the series.

@vcubingx 4 жыл бұрын

Thank you!

@COOLZZist 2 жыл бұрын

Wow, amazing way of visualization of non linear function and how data is transformed.

@kavinyudhitia 2 жыл бұрын

OOH MY GOSHHH THIS IS GREAT CONTENT. thanks a lot!!!!

@anupriyamagesh 3 жыл бұрын

Neural networks look simpler than these animations made. Fantastic job!

@NovaWarrior77 4 жыл бұрын

Another banger Vivek!

@Visualization101 4 жыл бұрын

Woahh, incredible! Happy to come this early :D

@ldx8492 4 жыл бұрын

Masterfully done, you managed to explain it in "simple terms, but not simpler"

@darmilatron Жыл бұрын

Thank you for your video, this is one of the best videos explaining neural networks that I have seen. Good Work

@sifiso5055 4 жыл бұрын

Another excellent video🙌

@doyourealise 3 жыл бұрын

who came here from canziani sir course? :) Loved the visualization bro

@rajeshviky 4 жыл бұрын

One of the best and most intuitive way of descibing neural network! You took it to next level... looking forward more from you :)

@vcubingx 4 жыл бұрын

Thank you!

@electronutlabs 4 жыл бұрын

Fabulous! Looking forward to the next in the series.

@morthim 4 жыл бұрын

one of the better talks on the topic. well done

@lightinrhythm8548 Ай бұрын

Insane 🎉🎉,,,,more strong visualisation videos

@YitzharVered 4 жыл бұрын

Wow! I've done things with neural networks before without even understanding the actual math behind it! Very enlightening!

@viveksurve5031 4 жыл бұрын

RT from THE three blue one brown, great work dude!

@rgoddard 4 жыл бұрын

Great video. Really looking forward to the series!

@t.gokalpelacmaz584 4 жыл бұрын

You have really developed man. Great progress and keep it up.

@gabrielguimaraes5628 4 жыл бұрын

Awesome video!!! Can’t wait for the next ones!

@amanasci2481 3 жыл бұрын

When is next part coming? Any updates?

@AnishBhethanabotla 3 жыл бұрын

hes in college now

@vcubingx 3 жыл бұрын

@@AnishBhethanabotla I am yes, but I'm currently working on the next part! I've scripted, recorded and made most of the animations, so I have some editing and reviewing to go but it should be out soon!

@mjf1422 4 жыл бұрын

This is amazing stuff. So many things I was able to understand that I couldn't get my head around before. Thank you so much!!! 😊

@gregvial 4 жыл бұрын

Great video! You were right, even as an experienced user of neural networks it helped me see things in a different way

@vcubingx 4 жыл бұрын

Glad to hear it!

@sitrakaforler8696 Жыл бұрын

Awesome content man. Bravo!

@Originalimoc 4 жыл бұрын

Interesting, looking forward to part 2😉

@patrickryckman3867 4 жыл бұрын

Absolutely awesome. Very informative and helpful for my visual mind. One thing I would love to see go along with your video, would be at the start you showed 3 neurons with 3 hidden layers. I would love to see a small dataset with perhaps 3 features, and follow along through with that throughout the whole video, and using real numbers so we could follow along and even work it out on paper if we wanted to. Anyways, Thank you so much for your awesome work. Subscribed!

@AWESOMEEVERYDAY101 4 жыл бұрын

This is too good. 3B1B vibes man

@gustavoexel5569 4 жыл бұрын

It would be nice to pay attention to the colors in the plots. I am colorblind, and at 6:52 it's almost impossible to see the boundary between the two colors.

@tristunalekzander5608 4 жыл бұрын

Well let me tell you they were beautiful and vibrant.

@deformercr6680 3 жыл бұрын

@@tristunalekzander5608 ... Talk about rubbing salt to a wound..

@hybmnzz2658 3 жыл бұрын

@@deformercr6680 you are pitying him for a condition he is already used to. I would argue that is worse than the pointless comment about how vibrant the colours were.

@deformercr6680 3 жыл бұрын

@@hybmnzz2658 it's not pity, it's being considerate. If you're eating some delicious food right in front of someone who can't eat, and then you start telling the person how tasty the meal is... I would say that's a little inconsiderate.

@hybmnzz2658 3 жыл бұрын

@@deformercr6680 if you tell someone who is lactose intolerant that your milk tastes good I think they would not care. And yes I think colourblindness is closer to that than the immediate sensation of tasting food in general. You meant no harm so I won't argue anymore. I just don't see it.

@arazsharma4781 3 жыл бұрын

Superb!! Eagerly waiting for the next videos! :D

@RedOneM 4 жыл бұрын

Thanks a lot, this definetly will become handy for my study just in a bit over a month.

@vtrandal 2 жыл бұрын

Excellent. Thank you!

@donbasti 3 жыл бұрын

Please make more, these are amazing!

@chrisr.3321 Жыл бұрын

this is suuuuuuuuuch a great video! Thanks

@ShivamVerma-gq2sm 4 жыл бұрын

Thanks a lot for such a vivid explanation ! Looking forward to more such content

@ricardoroxas7690 4 жыл бұрын

Nice! Looking forward to this series. 😁Imagine if we see an animation of an actual handwritten number image transformed into the decision "square"

@vcubingx 4 жыл бұрын

Good idea! I believe distill.pub has something like this

@lukejagg 4 жыл бұрын

He’s probably using publicly available data, so I doubt he’ll do an animation like that.

@nikhilyewale2639 3 жыл бұрын

Nice video.. Waiting for next chapter on visualising neural-nets !

@vcubingx 3 жыл бұрын

Working on it! It should be out soon

@MrDark-fm4gp 4 жыл бұрын

omg, I am so glad I found this channel

@mahdiamrollahi8456 3 жыл бұрын

I come from the new course by Alfredo and I dare say this was fantastic. Regards....

@SergioUribe 3 жыл бұрын

awesome explanation and video, kudos!

@vcubingx 3 жыл бұрын

Glad you liked it!

@AndreiMargeloiu 3 жыл бұрын

Part 2 and 3 please!

@devsutong 4 жыл бұрын

would be really great if this guy work out these videos with 3b1b... 3b1b is a very good educator

@mohsin-ashraf 3 жыл бұрын

Still waiting for the next most precious videos on the world of this series, please update.

@RobotProctor 4 жыл бұрын

Is this Manim? Nice work!

@agb2557 4 жыл бұрын

Great! Looking forward to the rest

@raresmircea 4 жыл бұрын

Kids today live at the beginning of the golden age of learning. I have a vague memory of reading a quote from Einstein where he said that art and science will eventually merge to bring a new way of representing reality. If he really said that, he was right! Our visual processing capacity is vast, and if we find sophisticated visual ways of conveying complex relations (through mediums like youtube, CGI, VR, AR) we will bring about kids that have superhuman abilities of grasping reality.

@plutophy1242 11 ай бұрын

love your series， it‘s so great

@user-vn9ld2ce1s 3 жыл бұрын

Sir, you have earned my subscribe, outstanding video.

@SamuelJFord 4 жыл бұрын

Subscribed. Excellent video!

@_coderizon 4 ай бұрын

Thank you! may i use the animation from 9:45 to 11:15 form this video for a creating a own video on this linear transformation?

@insightfool 4 жыл бұрын

Great work. I am still left wanting a more course overview which metaphorically explains how AI is not simply a series of input->hidden->output byt way of some narrative discussion and/or metaphore. Wanting that before I go deep into the linear algebra, and then reference the steps in the matrix max discussion with what was described in the initial narrative.

@aryanbhatia6992 4 жыл бұрын

thank you so much for making videos on deep learning , much neded.

@lalitvinde1441 3 жыл бұрын

Broooo it is awesome visualisation video😍,it makes foggy image of neural network fully cristal clear , i am really waiting for next chapter bro, when you gonna upload the next chapter....

@idos5049 4 жыл бұрын

Great video, love the animations!

@vasicnikola7674 4 жыл бұрын

Simply beautiful. Thank you

@MrDaanjanssen 4 жыл бұрын

Superb animation, well done

@user-dw6jd2ed7l 3 жыл бұрын

Great job , excellent

@felixakwerh5189 4 жыл бұрын

since you mentioned, sigmoid and relu i was hoping you would mention the softmax activation function and probably draw the graph as well, this is good video none the less

@KSK986 4 жыл бұрын

Thanks for these videos. Visualization provides powerful ways of understanding and these videos are of great help.

@yashkatare3303 4 жыл бұрын

You explained it really well. Really like the videos. Plus your voice is as soothing as Sal's.

@vcubingx 4 жыл бұрын

You think? Haha thank you so much, I don't think many people think that :)

@isax50 4 жыл бұрын

I love it great video! And thanks for sharing the course too! ...

@luketyler5728 4 жыл бұрын

Absolutely fantastic!

@victorvilanova3505 3 жыл бұрын

Awesome job! I love it!

@parmarsuraj99 4 жыл бұрын

Beautiful and intuitive!

@usama57926 4 жыл бұрын

When will the second video will out?

@tiosam1426 4 жыл бұрын

Thank you, KZfaq Algorithm, the Wise.

@youtubepooppismo5284 4 жыл бұрын

Handwritten-Digits are usually grayscale images, their pixel can be written in the form rgb(a, b, c) but since it's a grayscale image, a = b = c, so I can represent each pixel with only one numerical value. Given the matrix of those values I can then shove it into a linear vector and give it to the Neural Network. My question is; given a regular image with three (or even four) values for each pixel, how do I convert that into a vector? Do I just put the values next to each other or do I need to convert the rgb values into a single integer? Well the second one seems more reasonable since the first would add additional perceptrons to the Neural Network.

@vcubingx 4 жыл бұрын

One of the beauties of this idea of "learning" is that we don't actually need to worry about how we input the data, it just figures it out! Sometimes we don't even know what the data represents. As long as all the data is converted in the same way, it doesn't really matter! Here's an example: one time I used a neural network to play Super Mario Bros. The input to the network would've been a huge vector (iirc >65,000 inputs), which my laptop couldn't handle. Instead, I used the RAM of the console, which was just 128 inputs (not sure, I don't fully remember the number). However, I had no idea what each number represented! A lot of the time, our inputs are things that humans can't make sense of, but the neural network finds patterns among it. In reality, we don't use this "multilayer perceptron" I talked about in the video on colored images. Yann LeCun, the guy I talked about in the end, came up with something called "LeNet", or the convolutional neural network. I plan to make a similar video on the CNN, but it's gonna be a while before that comes out, so I encourage you to look it up! There are some fantastic resources on the web.

@vcubingx 4 жыл бұрын

To answer your question, it depends. The first example of just stretching it out would be ideal, because the second one can be a lossy compression. What I mean by that is if you add them, an RGB value of (60,0,0) is the same as (0,60,0).

@youtubepooppismo5284 4 жыл бұрын

@@vcubingx Thanks for the reply and the great advice, I will definitely follow it. However I think you misunderstood my second "guess" because that wouldn't be a lossy compression. What I mean by that is just converting an rgb value to an integer that represents it uniquely. rgb(0, 0, 0) -> 0 rgb(255, 255, 255) -> 16777215 (256^3 - 1) Which is literally just counting every possible rgb combination. If I remember correctly there are some pretty easy binary operations to make this conversion. Would this also work? Because if so, it'd be a smaller vector. Or it ould just mess everything up hehe Anyway, I will begin to seriously study this topic, also because I have a quite strong mathematical background so it shouldn't be too hard.

@kaifkohari5298 4 жыл бұрын

What a great explanation. 💯💯💯

@cwaddle 4 жыл бұрын

Great visualisatiom

@hamadsultan6861 4 жыл бұрын

Great Video!

@siddharthsahu1130 3 жыл бұрын

Thanks a lot where is the next video?

@HuyTran-ny7mg 4 жыл бұрын

absolut fantastisch. Thank you so much!

@vcubingx 4 жыл бұрын

Glad you enjoyed it!

@Studiousstudent885 Жыл бұрын

Thank you for this

@matron9936 4 жыл бұрын

Great video, waiting for the second and third part

@PapaFlammy69 4 жыл бұрын

11111

@gsjxbxbxhdhs5352 4 жыл бұрын

Flammable Maths suprise flame

@mahdiamrollahi8456 3 жыл бұрын

What will happen on samples on third quadrant? All of them aggregate to the central point? How this aggregation works following what we are going to lose about these samples?

@chaostrottel_hdaufdutube8144 4 жыл бұрын

Better than the 3b1b nn series

@manishbolbanda9872 3 жыл бұрын

so amazing.

@juliuscaesar467 3 жыл бұрын

Great video and explication maybe you should add a low sound classical music in the background like 3b1b

@PenguinMaths 4 жыл бұрын

This is awesome! It would be cool to make a tool to visualize actual trained neural networks on real data with this visual. Of course most real NNs have more than 3 dimensional feature space but it could be projected to 3 dimensions similar to google’s embedding projector. Have you considered something like this?

@vcubingx 4 жыл бұрын

Indeed! It's exactly what the next video is on!

@firSound 4 жыл бұрын

@@vcubingx Antsy

@DhananjayVenuri 2 жыл бұрын

I am excited with microchips neural networks wearable body gadgets being designed