AI Learns the Numbers

День тому

💚 Support Me on Patreon: / greencode
I decided to explore Pytorch and machine learning by teaching an AI the numbers. I used CNNs, neural nets, and even some complex networks (like AlexNet) to help the AI recognize the numbers. Hope you enjoy the video!
🔗 Link to Code:
drive.google.com/drive/folder...
📖 Awesome Coding Tutorials/Explainers:
Daniel Bourke: • Learn PyTorch for deep...
@mrdbourke (this man taught me everything I know about pytorch)
Backpropagation:
• What is backpropagatio...
• Back Propagation in Ne...
Convolutional Neural Networks:
• CNN: Convolutional Neu...
Music I Used in this Video: share.epidemicsound.com/7i1d0b
⭐ Other Social Media Links:
🔊 Discord: / discord
🐦 Twitter: / thegreen_coder
📸 Instagram: / thegreencoder
🎵 Tiktok: / thegreencoder
✨ Subscriber count: 38 subscribers.

КОМЕНТАРІ: 273

@Green-Code Рік тому

Thank you so much for watching☺! Make sure to check out the fundraiser💚: gofundme.com/raising-10000-for-diabetes-by-the-end-of-2022

@millionare5446 Рік тому

2022 already ended

@TurkeyTerrorizer Рік тому

@@millionare5446 NAAAAAH REALLY

@kpopandkdramalovers7740 Рік тому

Diabete

@Wonders_of_Reality Рік тому

I like your presentation, wit and pacing. But black backgrounds and white text is just killing my eyes. I do realise that the majority of artists like black environment. Just wanted to point out that a minority exists as well. It would be great if all the software would be switchable to a light mode for accessability reasons.

@aydink7739 Рік тому

Keep it going. Your production quality and also kind of self ironic style is fantastic.

@Green-Code Рік тому

Thank you so much! :)

@DanksterPaws Рік тому

His style reminds me of codebullet, I actually was a little confused because I clicked on this video subconsciously and I thought it was him for about the first quarter of the video.

@thirddrone Рік тому

@@DanksterPaws def codebullet inspirrd

@thisiso0_tron_0o41 Рік тому

Yeh feels like style has been stolen from code bullet. Still huge effort making this kind of videos

@Eren_Yeager_is_the_GOAT Рік тому

This deserves waaaaay more likes and views EDIT: wow already 256k views and 7k likes did not expect that in such a short amount of time

@Green-Code Рік тому

@GigantTech Рік тому

True

@HyperHrishiHD Рік тому

DEFINITELY

@brianwu3566 Рік тому

Honestly I think you can go above an beyond with res nets similar to resnet50 or alpha zero's net arch and then add a multilayered perception, it helps a lot with when compared to a fully connected layer(Alexnet). Truthfully speaking, just throwing more layers and neurons increases the accuracy, but also increases the chances of overfitting.

@zbyszekradzimi4066 Рік тому

The production quality on this is insane. When i clicked i thought it was 596 k subscribers not 596. Then i saw that when you made this u had 38. THATS CRAZYYYYYY. Subscribed and im probably gonna bingewatch your videos now. Your style reminds me of code bullets.

@Green-Code Рік тому

Thank you 💚

@Jason_vinion Рік тому

Also thank you so much for linking the code that’s awesome!!! And very very appreciated!

@Green-Code Рік тому

Of course!

@therealmstoltz7032 Рік тому

Awesome video! I did a 1st year engineering project that looked at different solutions to MNIST, our most accurate model was very similar to Alexnet but with some parameter / layer changes that let it get up to 99.7%. However, there are much less complex models that can reach the 99% mark.

@Green-Code Рік тому

Oh nice! 99.7% that's high!

@marklondon9004 Рік тому

Great stuff! Looking forward to seeing the rest of your work

@saud9947 Рік тому

WTF! I just saw you only have 100 subs?! With this quality you deserve more. You have my sub.

@saikhrisat1624 Рік тому

This is the first video of yours that was recommended to me on UKposts, and it was the best thing that happened to me today. Keep it up, bro. I enjoy your videos, but don't forget when you have more than 1 million subscribers 👻

@Green-Code Рік тому

Wow thank you dude. I won't forget :)

@NathanHedglin Рік тому

Absolutely amazing video. Great presentation style. Quality is above 99% 😊

@juaan_ Рік тому

Hey, first i wanna say I really like the style of the vid and its cool to be here when the channel is still small. Can I ask how did u learn to code, and how long have you been at it for?

@Green-Code Рік тому

Thank you so much! :D I started learning to code I think maybe 8 years ago. I mostly just watched tutorial videos and I built little projects. I'm still not great at it lol, but I have been slowly improving.

@Spindely Рік тому

@@Green-Code can you give some ideas of what to do in python? I wanna learn to use it but iam not sure what to do with it

@nithish.s8681 Рік тому

good job dude, you are keeping it straight forward

@GigantTech Рік тому

thank you very much for giving the code out to everyone

@_sahildahat_ Рік тому

Great video! Learned something new and would love to learn more!! Thank you!

@ltsben6564 Рік тому

Wow! This is incredible! I assumed because of your thumbnail and while I was watching the video that I was watching someone with 100k+ subscribers yet I've come to find you only have 385... I'll add another to start the way! I'm not much of a programmer, but this video and its style is incredible! I'm waiting for the video on Sunday ;)

@Green-Code Рік тому

Thank you so much man! You made my day :). I'm still editing today's video but it should be uploaded later today. Let me know if you like it 💚

@Destroyanad Рік тому

@@Green-Code Man u growin fast, already 1k subs

@puzzLEGO Рік тому

5:56 honestly that does look way more like a 7 than a 1 😂

@Green-Code Рік тому

Yep, my drawing skills are not the best 😂

@puzzLEGO Рік тому

@@Green-Code haha you did great! keep up the AI videos btw they have so much potential

@oienu Рік тому

I'm 120% sure is a 7, no one can think is another thing if you don't put a 7 at side for reference. Humans have the same problem trying to discern between a 0 and a O if you don't have a context.

@dedse3 Рік тому

Great video man, you make it interesting all the way until the end! I also checked your blog, nice article about science and code! +1 sub and share

@Green-Code Рік тому

Thank you bro, I appreciate that! I haven't touched the blog in a long time, but I'm very glad you enjoy it :)

@Covalact Рік тому

i just want to have a comment on your channel from the start of your journey to 100k , good luck you got it with an awesome content

@Green-Code Рік тому

Thank you so much :)

@asrar4907 Рік тому

Yo boi, dont you stop uploading these type of videos, you will one day reach a high feat, and 10k by the end of 2023 i wish i could donate but i dont have anything one me rn, keep going g

@Green-Code Рік тому

Thank you for the kind words :)

@Shannooty Рік тому

Been playing with mnist lately too, cool to see your results. Looking forward to more vids :)

@Green-Code Рік тому

Oh, that's so cool. Pytorch or Tensorflow?

@TheAznCoderPro Рік тому

This is such a well made video! You deserve way more subscribers. Keep it up!❤🎉😊

@Green-Code Рік тому

Thank you for the kind words! New video today :)

@zizohemid4356 Рік тому

Nice video format. Keep it up! The model sees numbers I can't see XD

@Green-Code Рік тому

You and me both XD

@usmonovjjs7490 Рік тому

Woow! Bro you explained very well! Amazing job 👍

@theuser810 Рік тому

I have also had the pleasure of completing the CNN course on Kaggle, This video came at a great time, also best of luck with your channel!

@Green-Code Рік тому

Thank you so much! I don't really know what course that is, but I hope it was interesting :)

@albertg4096 Рік тому

Amazing video! Will you make tutorials on how to do something like this? It would probably be the most informative tutorial on Machine Learning I've ever seen

@Green-Code Рік тому

Possibly :) (but not at the moment)

@jerin_stephen Рік тому

This is awesome man ... 🤙🤙🤙Keep rocking 🤙🤙🤙

@fragly Рік тому

I had to rub my eyes to make sure your sub count really said 386 subs and not 386k subs wildly underrated, excited to see more content

@Green-Code Рік тому

Thank you :D

@artemvolsh387 Рік тому

Great, thanks for the video. I personally like the details of implementation. If it's possible to create a video that would serve as a walkthrough of practice basics, that would be great learning material.

@Green-Code Рік тому

Thank you for the suggestion! I might do that in the future

@djvelocity Рік тому

*It is a crime that you have 4000 followers.* You deserve 4 million 🤯

@gavril3698 Рік тому

my homework on special mathematics subject in computer engeneering was literaly this :)

@Jason_vinion Рік тому

Wow this is amazing, may not seem like much now but this is top notice entertainment give it a few years and I have no doubt you’ll have quite a bit of subs (50k-100k) then it’s just growing after that

@Green-Code Рік тому

Thank you for the kind words :)

@danielabang6097 Рік тому

love the video man. Looking forward for future uploads

@Green-Code Рік тому

Thank you! More to come!

@FVT-tn8ji Рік тому

Thanks for the video, this was really interesting!

@iffathossain8050 Рік тому

The quality of this video is excellent. As an ML engineer, I suggest focusing on the F1 score on a previously separated testing dataset (There will be 3 divisions - training, testing, and validation). It would be best if you also created a graph from the history of training the model including the validation dataset. You see accuracy is not the one that we seek, we see how much pure the training has become. Also, it is essential to explain why you are applying a model, though most of the time, it's difficult to understand.

@Green-Code Рік тому

Thank you for the tip :)

@demonslime Рік тому

1:20 where did you get the model of my brain during exams from

@xmdani4165 Рік тому

Again amazing video! You should make more videos!!!

@alfashow2439 Рік тому

Nice viedo, you got me interested!

@Geosquare8128 Рік тому

Great video keep it up!

@ZenithCoding Рік тому

great intro to neural nets :D

@marcofe82 3 місяці тому

It's unbelievable how with your video I learnt a lot about AI. Thank u so much!!!

@Green-Code 3 місяці тому

Happy to hear that!

@thunder89 Рік тому

Two linear layers without any non-linearity as activation function in between is exactly the same as one linear layer. Think of a linear layer as (matrix) multiplication: out=weight1×(weight2×input) is the same as out=(weight1×weight2)×input . So the first two models are almost the same, just written a bit differently.. Thid explains why they perform the same..

@Green-Code Рік тому

Oh shit thank you for that

@grzegorzjanik4013 Рік тому

what tool did you use to visualize the convolutions?

@PotatoImaginator Рік тому

Very cool , i need to learn Machine Learning , Neural Networks too :)

@YahiyaJasem Рік тому

Great video ma man ,, i learned a lot

@sergi00 Рік тому

really good content oh and IM UR 100TH SUB LESGO

@Green-Code Рік тому

Let's go!!!

@jackparr4910 Рік тому

Amazing video! Did you use the same learning rates for all the models?

@Green-Code Рік тому

Thank you! Let me check :)

@Green-Code Рік тому

Okay, just check. I though it I set all the learning rates to be equal, but turns out that no. For the first and last model, the learning rate was 0.1. And for the other models it was 0.05. Thank you for pointing that out :)

@Harvey1G Рік тому

great video deserve more subs for sure

@Noirie99 Рік тому

You clearly deserve more subscribers

@Egon3k Рік тому

Cool Video :) reminds me a little bit of Code Bullet

@Sedquis Рік тому

The fact that I studied AI at university and this video was more understandable than my professor is crazy

@crazgon7261 Рік тому

Im in High School, and I have learnt more from my classmate than from my Physics teacher

@the_old_boy Рік тому

Thats a cool video. Hope to see more of it.

@Green-Code Рік тому

Thanks! Just posted a new video 😊

@vutrunghungnguyen1967 Рік тому

At the thumbnail, you should swipe the screen back and forth and you would probably see an illusion of that curve

@MysteriousPika Рік тому

Your really fun to watch, I’m to dumb to understand anything ur saying but it was a fun watch regardless

@Helmshot Рік тому

Now I know why my drawn numbers don't get recognized in games

@sandundeemantha34 Рік тому

I subscribed to you because you gave code

@maleek2.07 Рік тому

that was cool!

@aaronrobertcattell8859 Рік тому

What is backpropagation learning algorithm? Backpropagation, or backward propagation of errors, is an algorithm that is designed to test for errors working back from output nodes to input nodes. It is an important mathematical tool for improving the accuracy of predictions in data mining and machine learning.

@farhanaf832 Рік тому

Could you please make video about ML Alexnet how to code etc? Where did you learn it from?

@Green-Code Рік тому

There's some great tutorials out there on Pytorch and Tensorflow that are completely free. Check Daniel Bourke out!

@puppergump4117 Рік тому

Looks like you gained like 200 subs in 10 days. I guess you'll gain even more if you keep this up.

@Green-Code Рік тому

I'll guess we'll see :) New video this Sunday!

@darkchoco7407 Рік тому

Hello, why checking for accuracy and not f1-score? Thanks.

@Green-Code Рік тому

I just thought it would be easier :)

@stysan Рік тому

this video idea is not original and i saw it before, but still amazing realization!

@MasoodOfficial Рік тому

Good work.

@otter502 Рік тому

In the beginning you implied that the error was based on the distance between what it thought the number was vs what it actually was Wouldn't a better way to calculate the error to base it on shape? a 3 doesn't look like a 1 but the error (when based on values) is only 2

@Green-Code Рік тому

Yeah, you're right it calculates the error based on the shape :) It was just an easy explain what I was doing

@aoch1461 Рік тому

Fantastic!!!!!!!

@positivenozy6065 Рік тому

Hello! How did u study this AI subject? Is this what you are probably studying at university? I'm curious, want to study this topic, but need to know some sources to learn it. Could you help me?

@Green-Code Рік тому

I just learn it on my own :) Check out www.youtube.com/@mrdbourke

@positivenozy6065 Рік тому

@@Green-Code thanks!

@marcopozzi522 Рік тому

I'm studying to become a software architect so I don't understand anything about AI. Which linguage are you using? Are your program being executed on che GPU?

@Green-Code Рік тому

I'm using PyTorch (python) and yes my program is being executed on the GPU :)

@mohammadmemarnejad8014 Рік тому

In the second network I think the accuracy is low because the module is OVER FITTING I think if you decrease the number of nodes and find a normal threshold number the accuracy increases

@Green-Code Рік тому

Fair enough! Thanks for the suggestion :)

@josgielen8524 Рік тому

I wrote my own neural net in C#. With 1 hidden layer of 255 nodes it got 97.6% accuracy. With 2 hidden layers of 255 nodes each it also dropped to 92%. No idea why.

@Green-Code Рік тому

Wow, that's so interesting. Maybe it's overfitting?

@siddhantgupta1300 Рік тому

How or from where can i learn this

@markmanning2921 Рік тому

ok, but what can neural networks be used for besides recognizing images?

@Green-Code Рік тому

Watch the new video I'm going to post on Sunday and you'll see :)

@NotAFoe Рік тому

Subbed

@slacker2016 11 місяців тому

5:57 I honestly thought that was a seven too

@TheLuizfrds Рік тому

LOL, i did exactly the same thing when i was doing Computer Engineer!

@akhmalihsan5101 Рік тому

bro what's app did you use to calculate all that?

@Green-Code Рік тому

PyTorch (to make the machine learning model) and Adobe After Effects+Premier (to make the video)

@hugh_jasso Рік тому

Got lost in thought at "neuron." I don't have many of those left.

@mykytahordia Рік тому

I guess you have made visualization of dummy model a little bit wrong. There is no single hidden neuron. It has just flattened layer of input and dense connection with output layer, no hidden. also single neuron doesn’t make sense and can not reach 90%+ 😅. But anyway good vid

@Green-Code Рік тому

Yep 😅! You're absolutely right :)

@badalmukhiya149 Рік тому

Bro can you make any app related trading graphs plsss

@badalmukhiya149 Рік тому

Bro can you make the app for trading graph

@koufdell Рік тому

nice inspiration from ...... keep going

@j4sun Рік тому

Thank you so much, now I will build something so smart that politicians can be replaced

@Green-Code Рік тому

Okay, let me know how it goes

@hchattaway Рік тому

excellent video! Could you provide the requirements.txt file for this? Would help.. thanks!

@Green-Code Рік тому

All the code is linked in the description, you can run it by your self from google collab :). I guess the requirements.txt file is just what google collab has installed as a default. (if you run !pip list on google collab you can see all the requirements)

@hchattaway Рік тому

@@Green-Code the link in the description isn't to a CoLab notebook but just the notebook files themselves... I'll figure it out.. thanks!

@ArcamNight Рік тому

For AI is better to use TPU (TensorFlow Process Unit) if you use TensorFlow in your projects

@Green-Code Рік тому

Didn't know that, thank you😊

@ArcamNight Рік тому

@@Green-Code No problem mate 👍💪

@d2513850 Рік тому

Like optical character recognition technology

@Green-Code Рік тому

Same here

@HertzugLP Рік тому

Getting Code Bullet vibes here

@el_thesnipercraft Рік тому

your video are so great :😀

@realdragon Рік тому

Mission impossible: Teaching AI to read doctor's handwriting

@Green-Code Рік тому

😂😂😂

@Thegreatwizard122 Рік тому

like you're enthusiasm

@michaelbayer5887 Рік тому

... 3 - 6 - 9 - Tesla Numbers its realy enough to KNOW.

@Jordufi Рік тому

Model 2 doesn’t improve from model 1 because you are only using liner layers, try changing the activation function to relu

@randomhuman69420 Рік тому

Before watching this I thought he was going to train the models with the numbers from a bunch of different fonts...

@ShadowTB-ds4ks Рік тому

How about the other metrics?

@and_rotate69 Рік тому

U have

@Green-Code Рік тому

Maybe one day lol

@truestbluu Рік тому

Now we can tell Mason what the numbers mean.

@Outfled Рік тому

i actually gasped after watching the video and seeing youre only at 300 subs. great video nonetheless

@holz_name Рік тому

That's the problem, you can't really analyze the created net and figure out why it recognized a very well drawn 9 as a 3. The problem is even more of a bigger deal, because even pixels that have nothing to do with the number can screw up the net. Like add one white pixel on the edge and watch your net failing. Called Pixel Attack.

@r.d.l7236 Рік тому

But actually can someone tell why a model would predict a 9 to be a 3, even though it accurately predicted a 3 right initially in the same array of numbers. Is it memory issue? Not an expert, but this triggers interest. Great content.

@Green-Code Рік тому

Neural nets are kind of a black box, so I don't really know :)