AI Learns the Numbers
VloĆŸit
- Äas pĆidĂĄn 28. 06. 2024
- đ Link to Code: / 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!
đ Awesome Coding Tutorials/Explainers:
Daniel Bourke: âą Learn PyTorch for deep...
âȘ@mrdbourke⏠(this man taught me everything I know about pytorch)
Backpropagation:
âą What is backpropagatio...
âą Back Propagation in Ne...
Convolutional Neural Networks:
âą CNN: Convolutional Neu...
â Other Social Media Links:
đ Discord: / discord
đŠ Twitter: / thegreencoding
đž Instagram: / greencodecodes
đ” Tiktok: / greencodecodes
âš Subscriber count: 38 subscribers. - VÄda a technologie
Thank you so much for watchingâș! Make sure to check out the fundraiserđ: gofundme.com/raising-10000-for-diabetes-by-the-end-of-2022
2022 already ended
@@millionare5446 NAAAAAH REALLY
Diabete
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.
Keep it going. Your production quality and also kind of self ironic style is fantastic.
Thank you so much! :)
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.
@@DanksterPaws def codebullet inspirrd
Yeh feels like style has been stolen from code bullet. Still huge effort making this kind of videos
Also thank you so much for linking the code thatâs awesome!!! And very very appreciated!
Of course!
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.
Great stuff! Looking forward to seeing the rest of your work
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.
Thank you đ
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.
Oh nice! 99.7% that's high!
Absolutely amazing video. Great presentation style. Quality is above 99% đ
WTF! I just saw you only have 100 subs?! With this quality you deserve more. You have my sub.
This is the first video of yours that was recommended to me on CZcams, 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 đ»
Wow thank you dude. I won't forget :)
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
:)
True
DEFINITELY
Great video! Learned something new and would love to learn more!! Thank you!
Been playing with mnist lately too, cool to see your results. Looking forward to more vids :)
Oh, that's so cool. Pytorch or Tensorflow?
good job dude, you are keeping it straight forward
thank you very much for giving the code out to everyone
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?
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.
@@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
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
Thank you so much :)
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
Thank you for the kind words :)
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!
Thank you so much! I don't really know what course that is, but I hope it was interesting :)
This is such a well made video! You deserve way more subscribers. Keep it up!â€đđ
Thank you for the kind words! New video today :)
This is awesome man ... đ€đ€đ€Keep rocking đ€đ€đ€
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
Thank you bro, I appreciate that! I haven't touched the blog in a long time, but I'm very glad you enjoy it :)
Woow! Bro you explained very well! Amazing job đ
Nice video format. Keep it up!
The model sees numbers I can't see XD
You and me both XD
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 ;)
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 đ
@@Green-Code Man u growin fast, already 1k subs
Thanks for the video, this was really interesting!
Great video keep it up!
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
Possibly :) (but not at the moment)
love the video man. Looking forward for future uploads
Thank you! More to come!
Again amazing video! You should make more videos!!!
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.
Thank you for the suggestion! I might do that in the future
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
Thank you :D
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 youâll have quite a bit of subs (50k-100k) then itâs just growing after that
Thank you for the kind words :)
5:56 honestly that does look way more like a 7 than a 1 đ
Yep, my drawing skills are not the best đ
@@Green-Code haha you did great! keep up the AI videos btw they have so much potential
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.
Nice viedo, you got me interested!
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=weight1Ă(weight2Ăinput) is the same as out=(weight1Ăweight2)Ăinput .
So the first two models are almost the same, just written a bit differently..
Thid explains why they perform the same..
Oh shit thank you for that
*It is a crime that you have 4000 followers.* You deserve 4 million đ€Ż
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.
Thank you for the tip :)
1:20 where did you get the model of my brain during exams from
Great video ma man ,, i learned a lot
really good content oh and IM UR 100TH SUB LESGO
Let's go!!!
great intro to neural nets :D
my homework on special mathematics subject in computer engeneering was literaly this :)
5:57 I honestly thought that was a seven too
Thats a cool video. Hope to see more of it.
Thanks! Just posted a new video đ
Very cool , i need to learn Machine Learning , Neural Networks too :)
It's unbelievable how with your video I learnt a lot about AI. Thank u so much!!!
Happy to hear that!
great video deserve more subs for sure
Amazing video! Did you use the same learning rates for all the models?
Thank you! Let me check :)
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 :)
Now I know why my drawn numbers don't get recognized in games
what tool did you use to visualize the convolutions?
At the thumbnail, you should swipe the screen back and forth and you would probably see an illusion of that curve
You clearly deserve more subscribers
Cool Video :) reminds me a little bit of Code Bullet
I subscribed to you because you gave code
Your really fun to watch, Iâm to dumb to understand anything ur saying but it was a fun watch regardless
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.
Looks like you gained like 200 subs in 10 days. I guess you'll gain even more if you keep this up.
I'll guess we'll see :) New video this Sunday!
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
Yeah, you're right it calculates the error based on the shape :)
It was just an easy explain what I was doing
Could you please make video about ML Alexnet how to code etc?
Where did you learn it from?
There's some great tutorials out there on Pytorch and Tensorflow that are completely free. Check Daniel Bourke out!
The fact that I studied AI at university and this video was more understandable than my professor is crazy
Im in High School, and I have learnt more from my classmate than from my Physics teacher
Good work.
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.
Wow, that's so interesting. Maybe it's overfitting?
that was cool!
Fantastic!!!!!!!
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
Fair enough! Thanks for the suggestion :)
this video idea is not original and i saw it before, but still amazing realization!
... 3 - 6 - 9 - Tesla Numbers its realy enough to KNOW.
Like optical character recognition technology
Same here
Got lost in thought at "neuron." I don't have many of those left.
Model 2 doesnât improve from model 1 because you are only using liner layers, try changing the activation function to relu
nice inspiration from ...... keep going
Hello, why checking for accuracy and not f1-score? Thanks.
I just thought it would be easier :)
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?
I just learn it on my own :) Check out www.youtube.com/@mrdbourke
@@Green-Code thanks!
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 doesnât make sense and can not reach 90%+ đ . But anyway good vid
Yep đ ! You're absolutely right :)
How or from where can i learn this
Getting Code Bullet vibes here
Thank you so much, now I will build something so smart that politicians can be replaced
Okay, let me know how it goes
Subbed
For AI is better to use TPU (TensorFlow Process Unit) if you use TensorFlow in your projects
Didn't know that, thank youđ
@@Green-Code No problem mate đđȘ
bro what's app did you use to calculate all that?
PyTorch (to make the machine learning model) and Adobe After Effects+Premier (to make the video)
LOL, i did exactly the same thing when i was doing Computer Engineer!
Before watching this I thought he was going to train the models with the numbers from a bunch of different fonts...
like you're enthusiasm
Bro can you make any app related trading graphs plsss
ok, but what can neural networks be used for besides recognizing images?
Watch the new video I'm going to post on Sunday and you'll see :)
How about the other metrics?
i actually gasped after watching the video and seeing youre only at 300 subs. great video nonetheless
U have
Maybe one day lol
Bro can you make the app for trading graph
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?
I'm using PyTorch (python) and yes my program is being executed on the GPU :)
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.
Now we can tell Mason what the numbers mean.
5:57 ok even I thought that was a 7
Why don't they put the bar on the seven ? All the seven look like ones
where is the link for the AI at ?
In the description I believe :)
Mission impossible: Teaching AI to read doctor's handwriting
đđđ
now train a Vision Transformer
nice channel, and good news for you: the youtube algorithm chose you
I guess so :)
You fail to mention that your dog is named "diabetes"..... :>