Hope you enjoy the course :-) Check out my channel for more things like this, and btw. I'm organizing a creative coding competition (the main video on my channel tells about it, if interested).
You could teach backpropagation by using a convolution neural net that clasifies things ( maybe it can recognize digits or letters CNN OCR) , then you can imput the characters or digits from keyboard and the ai will generate the image for that character via backpropagation ( or at least we would see a representation on what the network thinks it represents) Ofc, the most challenging part would be to offer a background of matrix algebra, partial derivatives for gradient descent, activation functions for perceptrons, function composition, and i thing that should be the bare minimum. Anyways, keep doing what you do, i enjoy your work ! PS: i have tried it with cats ( you wont belive the abominations )
@@Alex_AlyI can teach it also with the same setup from here as well, no need for convolutions... But I don't know how to teach it well at the moment (if I ever teach it, I want to make it accessible). In phase 3 of the self-driving car course (coming in January) I will teach neural networks in an understandable way. I will probably include something about gradient descent, but my main goal is to explain what neural networks can do and what complexity (number of neurons) is needed for different tasks. I feel this kind of content is completely lacking online...
I had been waking up to the same video for the past 6 months but never thought to read comments. It is so mysterious!!! UA-cam are you trying to teach us neural networks from scratch in our sleep?? WHY?!!
@@theuniverse2268 I agree with what you’re trying to say, but it really all can be proper and we probably couldn’t have understood much of this unless we saw that stuff prior, maybe
Thanks so much for the tut and I'm looking forward to part 3 of this course. I'm gonna try to implement something similar on a smaller scale to help teach and get kids excited about ML. for reference how could I improve on the MLP for a better accuracy without overfitting? (Ps. Radu you are amazing just for the fact that you are still replying to comments so a special thank you🌟)
There is one ML tutorial aimed at high-school students. You may find it useful: ua-cam.com/video/QXB1ytG95gs/v-deo.html I don't really have tips I could give for avoiding overfitting. At least none I can summarize here as a comment.
Dear channel owners, please provide edited subtitles for all your videos. This will greatly assist people with hearing impairments. Automatically generated subtitles contain many errors. Accurate information is crucial in programming. Thank you.
@@MarcosLopez-nd8tg yeah... that's exactly the reason. I spend 1 hour to add subtitles for 10 - 15 minute videos. And it's not something fun :-| can't listen music or do anything like that during it because have to listen to what I'm saying... I'm grateful that UA-cam automatically generates the captions, and that they are helpful at least somewhat.
I downloaded the starting code as is and ran "npm install" but got an error. Got the same problem in the last video when I couldn't install the canvas package. Node works fine for every other thing I use it for. Can someone advise why this happens
About node.js, just in case someone is having the same trouble. By default, I'm using the version v20.1.0, but when I run `npm install`, it throws some errors, and the installation fails. I solved it switching to a previous version of node, v18.16.0 (in the video Radu uses v18.12.0, so probably every v18.x.x will work fine).
We do use python's scikit-learn in the course to learn what it can do and we do get a decent result using it. It's a good library even though python has ones more tailored for neural networks nowadays (tensorflow, pytorch, keras). But I doubt we could get some better results using those. Instead, I would focus on tailoring the features. Probably applying convolutions to the pixels would be a logical next step.
The data (~5400 samples) is so big that my browser is not able to load the "viewer.html" page ("page becomes unresponsive"). Is there any way to solve this problem?
I tried with less data it worked, but accuracy was less . But smaller thumbnails idea is better option since accuracy is more. Thanks for the idea 😃@@Radu
Haha, yeah, it's what happens when you have a while loop doing a bunch of things like that. Games have time to process between each frame. The goal is to update just 30 times per second or so.
:-) yeah, I think it's important to show that a machine learning model doesn't depend on a programming language. And that using the model is relatively cheap compared to the training step.
We will have a little bit of an unbalance after the data cleaning (not anymore the same number of items of each class). But I don't focus on this problem in the course. But in short... you have to figure out if the data is expected to be balanced or not. If it is, you should probably create a subset of the data to balance it out and then do the training. But if not, you may do more harm than good if you try to classify underpopulated classes... Really depends on the scenario (like if the underpopulated classes are really important for some reason, then you have to do something else).
No one uses JS for machine learning, it’s the worst you can do. Please add JS to the video title so no one gets confused and no one watches the video. I know JS and Python, so I’m not saying this cause I know only Python
Thanks for the feedback! I don't have control over the video title... But I argue that since it says 'without libraries' it won't make a difference. I mean, coding this in python is as difficult if you don't import anything. This tutorial focuses on why those ML techniques work, it doesn't try to get things done quickly.
Yes, JavaScript libraries suck... but they also exist because... JavaScript sucks. I have been using JavaScript since 1994... I know this for a fact. You're using JavaScript for this because... you only know JavaScript. Sorry, it's just reality.
Hope you enjoy the course :-)
Check out my channel for more things like this, and btw. I'm organizing a creative coding competition (the main video on my channel tells about it, if interested).
You could teach backpropagation by using a convolution neural net that clasifies things ( maybe it can recognize digits or letters CNN OCR) , then you can imput the characters or digits from keyboard and the ai will generate the image for that character via backpropagation ( or at least we would see a representation on what the network thinks it represents)
Ofc, the most challenging part would be to offer a background of matrix algebra, partial derivatives for gradient descent, activation functions for perceptrons, function composition, and i thing that should be the bare minimum.
Anyways, keep doing what you do, i enjoy your work !
PS: i have tried it with cats ( you wont belive the abominations )
Amazing sir. u are the best
@@Alex_AlyI can teach it also with the same setup from here as well, no need for convolutions... But I don't know how to teach it well at the moment (if I ever teach it, I want to make it accessible). In phase 3 of the self-driving car course (coming in January) I will teach neural networks in an understandable way. I will probably include something about gradient descent, but my main goal is to explain what neural networks can do and what complexity (number of neurons) is needed for different tasks. I feel this kind of content is completely lacking online...
Absolutely
Doc, you're the best!!
I had been waking up to the same video for the past 6 months but never thought to read comments. It is so mysterious!!! UA-cam are you trying to teach us neural networks from scratch in our sleep?? WHY?!!
when i wake up i always either see a 12 hour minecraft video, 4 hour proggramming course, or space X documentation for some reason
Yes, mine is mainly this kind of video
i just woke up
Bro same lol
Me too i didnt play this video
Me too bro hahahahhaahhaah
Bruh me too.
same
why did i wake up to this
DUDE FUCKING SAME 🤣🤣
Bro's im not kidding, i really did wake up to this, these guys must be experimenting woth the algorithms.
Just woke up to this, idk why
When I read "without libraries": I was very amazed.
Yes. Finally a proper machine learning study material lol
@@theuniverse2268 I agree with what you’re trying to say, but it really all can be proper and we probably couldn’t have understood much of this unless we saw that stuff prior, maybe
Was it without library? Just starting watching? Any good?
oh yeah best thing to wake up to. 3 hour video on neural networks
Never mind your vast knowledge on various things, I specifically want to thank you for knowing how to teach.
Happy to hear things like this. Thank you :-)
Will complete because of its "no blackbox" approach. Will get better idea
Good luck! :-)
Coding without libraries is true coding.
:-)
I've seen this guy before. He makes really good content! I'm sure I will learn a lot from this. 💡🙂👍🏻
:-)) thanks
This is amazing. You gotta love it and learn many from Radu
Haha, thanks :-)
Amazing, I'm excited to learn. I'll complete this course with practice
Good luck! :-)
You are the best Radu. Keep making videos.
One word for this video , Amazing
I have given thumbs down and said "nor interested" to these videos over and over and youtube keeps sending me here in my sleep. Damn you algorithm.
:-))
Congratulations and greetings from Colombia
Thanks so much for the tut and I'm looking forward to part 3 of this course. I'm gonna try to implement something similar on a smaller scale to help teach and get kids excited about ML. for reference how could I improve on the MLP for a better accuracy without overfitting?
(Ps. Radu you are amazing just for the fact that you are still replying to comments so a special thank you🌟)
There is one ML tutorial aimed at high-school students. You may find it useful: ua-cam.com/video/QXB1ytG95gs/v-deo.html
I don't really have tips I could give for avoiding overfitting. At least none I can summarize here as a comment.
this is amazing, I finally completed and learned a lot
Glad to hear :-)
Self driving car was a blast... Can't wait to get on this
Self-driving car Phase 2 begins in the second half of September (on my channel) ;-)
Hey you, you're finally awake...
This is the 3rd time I’ve woken up to this video
WHAT A BADASS VIDEO THANK YOU
You're welcome :-)
Thank you for sharing this awesome tutorial
You're welcome!
Glad I'm among the first people to watch this video ❤😂😂
I woke up and i was here.. but why????
Got the same thing 😅
Same dude😂
Why does PBS Spacetime keep autoplaying to this dude?
Is that what happened? I fall asleep listening to PBS Spacetime & then randomly woke up to this video playing one night.
Terrific
What amazing Channel
3 am and woke up to this like almost everyone here
Dear channel owners, please provide edited subtitles for all your videos. This will greatly assist people with hearing impairments. Automatically generated subtitles contain many errors. Accurate information is crucial in programming. Thank you.
It's a 3 hours 37 min long video😐
@@MarcosLopez-nd8tg yeah... that's exactly the reason. I spend 1 hour to add subtitles for 10 - 15 minute videos. And it's not something fun :-| can't listen music or do anything like that during it because have to listen to what I'm saying... I'm grateful that UA-cam automatically generates the captions, and that they are helpful at least somewhat.
@@RaduSorry to hear that. Btw great video!
@@MarcosLopez-nd8tg Thank you!
Please bring the Algorithms 1, 2 of princeton university.........
5.4k views 2 hours ago
I'm here early🙂
I downloaded the starting code as is and ran "npm install" but got an error. Got the same problem in the last video when I couldn't install the canvas package. Node works fine for every other thing I use it for. Can someone advise why this happens
Can you give more details about the error?
1:18:00 you could use also jarvis algo for the same
yes
Thank You ❤️
About node.js, just in case someone is having the same trouble.
By default, I'm using the version v20.1.0, but when I run `npm install`, it throws some errors, and the installation fails.
I solved it switching to a previous version of node, v18.16.0 (in the video Radu uses v18.12.0, so probably every v18.x.x will work fine).
Oh wow, thanks for pointing this out :-|
Oh! This is my Wish❤❤❤
Haven’t started the course yet, but I do have a question. Say you have to do it for real, what libraries should you work with to accomplish this?
We do use python's scikit-learn in the course to learn what it can do and we do get a decent result using it. It's a good library even though python has ones more tailored for neural networks nowadays (tensorflow, pytorch, keras). But I doubt we could get some better results using those. Instead, I would focus on tailoring the features. Probably applying convolutions to the pixels would be a logical next step.
How did i emd up here
I love freecodecamp courses which is amazing 😍😍😍
Great 👍
Woke up to this
The data (~5400 samples) is so big that my browser is not able to load the "viewer.html" page ("page becomes unresponsive"). Is there any way to solve this problem?
You can try using less data. Or maybe draw the thumbnails as smaller images 200x200. Those should help.
I tried with less data it worked, but accuracy was less . But smaller thumbnails idea is better option since accuracy is more. Thanks for the idea 😃@@Radu
@@duke_adi No problem!
i woke up to this, why is youtube bringing us together??
now my gaming laptop is dying while generating data and for feature extration too
Haha, yeah, it's what happens when you have a while loop doing a bunch of things like that. Games have time to process between each frame. The goal is to update just 30 times per second or so.
@@Radu lol master you replied to your student it means a lot
@@meganova609 :-)
I also woke up to this
Hey, can you also share the link for the part1
It's the first one in the description.
Python will do the heavy lifting? this is weird and no way I am missing this video.
:-) yeah, I think it's important to show that a machine learning model doesn't depend on a programming language. And that using the model is relatively cheap compared to the training step.
@@Radu yes. You are correct.
How do i handle unbalanced dataset
We will have a little bit of an unbalance after the data cleaning (not anymore the same number of items of each class). But I don't focus on this problem in the course. But in short... you have to figure out if the data is expected to be balanced or not. If it is, you should probably create a subset of the data to balance it out and then do the training. But if not, you may do more harm than good if you try to classify underpopulated classes... Really depends on the scenario (like if the underpopulated classes are really important for some reason, then you have to do something else).
No one uses JS for machine learning, it’s the worst you can do.
Please add JS to the video title so no one gets confused and no one watches the video.
I know JS and Python, so I’m not saying this cause I know only Python
Thanks for the feedback!
I don't have control over the video title... But I argue that since it says 'without libraries' it won't make a difference. I mean, coding this in python is as difficult if you don't import anything.
This tutorial focuses on why those ML techniques work, it doesn't try to get things done quickly.
Can you give me the link of the first section
It's the first link in the video description.
30:00
01:03:00
Good morning boys
Why JavaScript? Why not Python
I explain why here 03:08.
I am going to learn thia and comeback to gift $100. Now at 0:0
How far?
Please teach about dbms
i have a good question?
What is your question.
2:26:00
course :-)
З.Ы: мне бы хотелось найти начало ( у меня всё в виде HDD лежат стопкой на полке :) и пока не возможно их куда либо в монтировать)
...
з:ы: у меня дафомин зашкалил когда это увидел :))
Hello
JS...
Im going back to sleep
Я 2 года в коме был только начал осознавать
❤
56K
I managed 10 seconds. then no.
any one using nature language to query database ?
p
we R, We are full of life and Alive, so what is the chances of saving the earth in 500,000,000 years or so? to be honest and just a kick
Друг Я надеюсь что ты не все картинки раздел
33732
Algo😂
🎉❤
someone says
pp
First viewer
Yes, JavaScript libraries suck... but they also exist because... JavaScript sucks. I have been using JavaScript since 1994... I know this for a fact. You're using JavaScript for this because... you only know JavaScript. Sorry, it's just reality.
:-)))) funny because this whole academic year I only teach Python and C# at work.
ppp
What the foak did i just watch
😅6th
First
@freecodecamp
You never cease to impress!
Nice thank you so much 👌👍🙏🫶🤝✌️👏🙌
No problem!
p
p