Learn how to code a simple Convolutional Neural Network with this fully annotated Jupyter Notebook: lightning.ai/lightning-ai/studios/build-train-and-use-a-convolutional-neural-network The full Neural Networks playlist, from the basics to deep learning, is here: th-cam.com/video/CqOfi41LfDw/w-d-xo.html Support StatQuest by buying my book The StatQuest Illustrated Guide to Machine Learning or a Study Guide or Merch!!! statquest.org/statquest-store/
Hey josh, is that possible to make videos about rcnn, fast rcnn, faster cnn & yolo I watched some videos and read some paper, didnt clear explain math part(only understand basic concept) Especially how to caculate selective search, how to train(one image contain many classification, how to train when we have many many images)
I can't imagine how much time and effort you put for: 1. Creating the content and simplifying it for us 2. Create the animated ppts 3. Explaining every step with great detail and simplicity I just wanna give a huge hug to you sir! You are an asset. ❤❤
Hi thanks for the great video! Always enjoy your videos! However, may I ask a burning question? The feature map and the pooled values contain information from the initial image, but how do they describe/represent how does the image actually looks like? I don't quite understand how the output of the dot product or the pooling can help in the understanding of how the image looks like.
As a Cambridge qualified PhD Mathematician, I cannot begin to describe how fantastic your series are. The way you simplify the concepts, yet keep true to the underlying Mathematics is quite amazing. Not to mention the great animations, dynamic graphs and equations, etc. Well done Josh, for making principled data science accessible to the general audience.
Amazing work. I'm started learning DS and I can't imagine how I can handle all of this information without your videos. Big thanks for everything you've done, do and will do
The Moment I Saw The first video of this series , I immediately placed an order of the book ! Cant Describe How well u are explaining. Blessed To Have TH-camrs Like You .
That book is already > 300 pages long, so I decided to write a separate book all about neural networks that will include CNNs. I'm working it right now.
Hi Josh. Thank you so much for these videos. All videos you do are fun and so easy to understand. Without any doubt when I see your explanations I can conclude that things are not difficult, they are just badly explained. Your explanations are fantastic. I decided to support you. I am sorry I cannot provide the amount you deserve for such a quality education, but I am merely a student. However, I will not forget you when my condition improves. Please do not stop helping us.
I can't stop thanking you for your content! I am a master in data science student and usually before engaging with the commonly unfathomable statistical learning books I come to your channel to grasp the topics.
I was a undergrad poli-sci data analytics student three years ago. I couldn't imagine myself going into data science because I know I am not a STEM student nor do I have a great working brain for math. But when I watched your videos back then, I was able to get confidence that I can give myself a chance to study DS which I love. Here, three years later, I am in the MSDS program at Columbia University studying data science. This was only possible because of your ml/stats videos. I still find myself studying your videos to understand concepts, which allows me to read the text without spending countless days stuck. I sincerely thank you very much for giving me a chance to actually dive on such a complex but cool subject.
This is the best explanation for CNN I have ever come across. I am very sure this is best I will ever see. I cannot you thank you enough. I have had explanations from my instructors who are PhD, MTechs and what not!! even they could not explain why filters are able to extract features and why we use global pooling. The answer I got was to reduce the number of inputs nodes to NN (which is partly true also) but the way you have explained the importance of pooling, I was amazed and equally happy to see. Thank You Josh Sir. I think you should be knighted for your efforts 😃👏🏻👏🏻👏🏻👏🏻👏🏻
Thanks for the video! I watched (and took notes) of the whole Neural Network series :) Like others have said: you explain difficult concepts in such an elegant simple way, while staying true to the basic mechanisms of the concept.
The best CNN explanation I've ever seen. However, i have one question about the part of classification of 0 or 1. As a classification problem, why there is no sigmoid or softmax function used in the last layer, are we just using the raw output to make prediction?
Typically you would probably want to use softmax paired with the cross entropy loss function for this sort of problem. However, to keep the network as simple as possible (i.e. in order to fit it on the screen) and because the math still worked out, I just used the sum of the squared residuals of the raw output to train this CNN. I was surprised that it worked, but it did! BAM!
I was really confused on this concept before I came across this video, now I feel I understand it way better. You really helped a lot! Thank you so much!
Great video! And would like to ask a question ---- How is the first filter computed by Back propagation (it started with random values in the 3*3 pixels, then it was adjusted by BP). And if i break down the question to sub-questions (a) What loss function is used in this BP. (b) And the gradient used in BP is with respect to who? Thanks again for the great content!
In this specific case, the loss function is the sum of the squared residuals, but cross entropy is much more commonly used in this situation. The gradient is with respect to each parameter we want to estimate (so each square in the convolutional filter, each bias, each weight etc.)
Thank you Josh!!! You truly are the best at explaining these concepts. I would love to see future videos on how to train the kernels, and more on image recognition/computer vision (clearly explained of course). I also got your book and it's really nice, maybe there can be a part 2 in the future 👀
I really enjoyed it; although I'm somewhat familiar with the CNN, bbut the part where pooling basically rewards the match between the filter & the image clicked :] best,
This was an amazing video! However, I'm a bit confused about how higher complexity neural networks work? From other sources I have read that CNN's can have multiple convolutional layers, but this doesn't make sense to me. If convolution is used to get a general map of features from the input, and you use max pooling to get values which you input into nodes and you calculate weighted sums etc how can you reapply convolution in a further layer?
@@statquest What would it mean to add them at the end? Like at the start it makes sense as we are trying to map the features of the input image, but at the end what are you achieving by adding more convolutional layers?
@@bowlteajuicesandlemon You could just create additional inputs to the final fully connected NN. That would allow you to combine the different features you detect with the filters.
I have a question. Can you have more than one filter in order to identify sub patterns? For example you could want to identify the main sub shapes that make up numbers from 0-10 (circles, lines, diagonals) as another hidden layer before guessing the correct number. Is this actually needed/correct? Thank you
"I don't know how much time does Artificial Neural Networks take to train, learn the input data, But you are putting more efforts and it taking much time in your training time".Thanks to your efforts sir. , your videos really explains very well and it helps us in visualizing easily.
Hey there, thanks so much for this video! It helped me way more than my university masters degree course material :) I was just wondering if you were planning on creating videos on the following topics: - Recurrent Neural Networks - Transformer Neural Networks - Graph Convolutional Networks - Deep Generation Models. Would be awesome! Cheers :)
Hi Josh, you know you are awesome, you know you and I both are in this domain and I have also started learning to play guitar. I hope this channel will help me in my journey.
All of your videos are amazing. You are very talented to explain complicated things in a simple way. I am looking forward to seeing embedding, attention and transformers videos from your point of view.
if not this video and you learn the Neural Networks in picture classification in book, you need spend a total afternoon and finally you may feel you are stupid. Now in StatQuest you only need spend half an hour
Thankyou. Thankyou! You are amazing master of explaining things... break it down to the smallest chunk and and build it up in step by step. I very much look forward for more marching learning tutorial. There is lot of tutorial out there and I spend lot of time understanding it but nothing match the the way you explain. Thank you Tons for awesome contents you have created and the insights you provide
I've never seen such a simple yet very good explanation of a CNN. Thanks a lot! As a non-native english speaker I really love the simplicity and the written texts in your videos.
What I could make of this video is that once the filter, its bias and are tuned through back-propagation and appropriate activation function is selected, after max pooling its vector is fed into the ordinary neural network which learns to classify whether such kind of matrix could come from X or O.Have i understood correctly..? Also the max pooled vector/matrix will fill 0s and 1s in relatively unique ways (for X and O) depending upon how the filter has matched to the original image.That forms basis for classification..!!
I love your videos, I have binge watched your entire machine learning series. One suggestion I might add is the following: It can be confusing to use 1s to represent black pixels and 0s to represent white pixels, because in Computer Vision a black pixel has a value of 0 and a white pixel has a value of 255. So when normalized Black = 0 and White= 1. Thank you so much for these videos btw I love them.
@@statquest Most of who watch your videos are in the Software/AI field, it would be really helpful for beginners like us if you implement the Python code (From scratch, without using external libraries like SciKit learn, Keras or Tensorflow) it would be so much helpful for us. Also, thanks for the effort you put in your videos, my Machine Learning journey is becoming way easier because of your great explanation.
I literally binged your neural network videos in a day like a Netflix show and now realized that I am at the end of the series to date and I need to wait for a new episode!
Hi Josh! First of all let me tell you that your youtube channel is amazing! Thank you for that! Also, I would like to know if you are going to release any content about 1D Convolutional for Time Series Data? Have a great week! Thanks!
Not in the immediate future. For time series data, I've been describing RNNs: th-cam.com/video/AsNTP8Kwu80/w-d-xo.html and LSTMs: th-cam.com/video/YCzL96nL7j0/w-d-xo.html
![The moment we stopped understanding AI [AlexNet]](http://i.ytimg.com/vi/UZDiGooFs54/mqdefault.jpg)
Learn how to code a simple Convolutional Neural Network with this fully annotated Jupyter Notebook: lightning.ai/lightning-ai/studios/build-train-and-use-a-convolutional-neural-network
The full Neural Networks playlist, from the basics to deep learning, is here: th-cam.com/video/CqOfi41LfDw/w-d-xo.html
Support StatQuest by buying my book The StatQuest Illustrated Guide to Machine Learning or a Study Guide or Merch!!! statquest.org/statquest-store/
Great playlist! Can you also make a video on variational autoencoder networks?
@@evelinewuytens2890 I'll keep that in mind.
Hey josh, is that possible to make videos about rcnn, fast rcnn, faster cnn & yolo
I watched some videos and read some paper, didnt clear explain math part(only understand basic concept)
Especially how to caculate selective search, how to train(one image contain many classification, how to train when we have many many images)
@@bennybenbenw I'll keep those topics in mind.
I can't imagine how much time and effort you put for:
1. Creating the content and simplifying it for us
2. Create the animated ppts
3. Explaining every step with great detail and simplicity
I just wanna give a huge hug to you sir! You are an asset. ❤❤
Wow, thanks!
@@statquest for real! This is amazing! Thank you so much
4. Writing the song lines and adding attractive music to them to add some entertainment to the whole matter
Yes he is
Oh my goodness! this is the simplest way CNN has ever been explained while still keeping true to the Maths. Thanks so much, Josh!
Glad you liked it! :)
Thank you a lot!! Your videos are the best!!
Glad you like them!
Hi thanks for the great video! Always enjoy your videos!
However, may I ask a burning question?
The feature map and the pooled values contain information from the initial image, but how do they describe/represent how does the image actually looks like? I don't quite understand how the output of the dot product or the pooling can help in the understanding of how the image looks like.
See 7:21 for the feature map. For pooling, see 8:20
As a Cambridge qualified PhD Mathematician, I cannot begin to describe how fantastic your series are. The way you simplify the concepts, yet keep true to the underlying Mathematics is quite amazing. Not to mention the great animations, dynamic graphs and equations, etc. Well done Josh, for making principled data science accessible to the general audience.
Wow! Thank you very much!
As a person with a PhD in Subjective Applied Mathematics from the University of American Samoa, I approve this message
Josh needs to be on brilliant,can you guys help
You saved my life. The best CNN explanation I've ever seen
Hooray!
why did it save you? do u have Neural Network homework or what?
Eagerly waiting for LSTM and it's varients. awesom explaination ...
Noted
@@statquest And GRU, please!
Amazing work. I'm started learning DS and I can't imagine how I can handle all of this information without your videos. Big thanks for everything you've done, do and will do
Thank you very much! :)
Please consider doing an NLP series from regression to bert
I'll keep that in mind.
I think transformer and self-attention is a very hard topic for explain, so let him some time.
@@buithanhlam3726 True. It was just a suggestion for the future.
@@xiaoqingwan1912 noted! :)
I third that! Would love to see an NLP series.
The Moment I Saw The first video of this series , I immediately placed an order of the book ! Cant Describe How well u are explaining. Blessed To Have TH-camrs Like You .
Thank you!
As a PhD candidate in machine learning at Harvard, I cannot stress how simple and beautiful your videos make complex concepts. Well done
Thank you!
Why am I not able to stop the playlist? Why am I still not bored!?
Great effort in making things simple and fun. BAM!
Thank you!
Somehow "bam~" has become my own pet phrase in real life.
bam! :)
Why CNN doesn't show up in your The StatQuest Illustrated Guide to Machine Learning (PDF)?
That book is already > 300 pages long, so I decided to write a separate book all about neural networks that will include CNNs. I'm working it right now.
@@statquest thank you!!
You are a gift of God to the education of Machine Learning!!!! Thank you so much!!
Thank you!
Another simple and human-readable explanation of the rather complex concepts of Neural Networks.
Thank you!
I feel I need a StatSquatch plushie in my life ❤
Aww!!! That would be awesome!!! I'll look into it!!! BAM! :)
Everytime I see a new video from you I feel like I got a GOLD coin for free. Thank you Sir!
Awesome!!!
My favorite channel to do with all things data has finally done a video on my favorite data science topic... TRIPLE BAM!
Hooray!
BEST CNN VIDEO IN THE INTERNET
bam! :)
Ive seen multiple videos on CNN and nothing made me understand convolution, but this! Thanks statquest
BAM! :)
Just wanted you to know that I'm earning my bread and butter just because of you. Thank you teacher!
Congratulations! BAM! :)
Hi Josh. Thank you so much for these videos. All videos you do are fun and so easy to understand. Without any doubt when I see your explanations I can conclude that things are not difficult, they are just badly explained. Your explanations are fantastic. I decided to support you. I am sorry I cannot provide the amount you deserve for such a quality education, but I am merely a student. However, I will not forget you when my condition improves. Please do not stop helping us.
Wow! Thank you very much! It means a lot to me that you care enough to contribute. :)
I can't stop thanking you for your content! I am a master in data science student and usually before engaging with the commonly unfathomable statistical learning books I come to your channel to grasp the topics.
BAM! :)
I was a undergrad poli-sci data analytics student three years ago. I couldn't imagine myself going into data science because I know I am not a STEM student nor do I have a great working brain for math. But when I watched your videos back then, I was able to get confidence that I can give myself a chance to study DS which I love. Here, three years later, I am in the MSDS program at Columbia University studying data science. This was only possible because of your ml/stats videos. I still find myself studying your videos to understand concepts, which allows me to read the text without spending countless days stuck. I sincerely thank you very much for giving me a chance to actually dive on such a complex but cool subject.
WOW!!! Congratulations!!! That is awesome. It's an honor to be a small part of your success and it motivates me to do more. Thank you!
This is the best explanation for CNN I have ever come across. I am very sure this is best I will ever see. I cannot you thank you enough. I have had explanations from my instructors who are PhD, MTechs and what not!! even they could not explain why filters are able to extract features and why we use global pooling. The answer I got was to reduce the number of inputs nodes to NN (which is partly true also) but the way you have explained the importance of pooling, I was amazed and equally happy to see. Thank You Josh Sir. I think you should be knighted for your efforts 😃👏🏻👏🏻👏🏻👏🏻👏🏻
Thank you! :)
Sir Josh Starmer first of his name ,the ruler of StatQuest realm 🙏
@@liviumircea6905 Ha! you made me laugh. :)
Thanks for the video! I watched (and took notes) of the whole Neural Network series :) Like others have said: you explain difficult concepts in such an elegant simple way, while staying true to the basic mechanisms of the concept.
Awesome, thank you! And thanks for your support!
Thank you very much you are saving my master's degree
Good luck!
The best CNN explanation I've ever seen. However, i have one question about the part of classification of 0 or 1. As a classification problem, why there is no sigmoid or softmax function used in the last layer, are we just using the raw output to make prediction?
Typically you would probably want to use softmax paired with the cross entropy loss function for this sort of problem. However, to keep the network as simple as possible (i.e. in order to fit it on the screen) and because the math still worked out, I just used the sum of the squared residuals of the raw output to train this CNN. I was surprised that it worked, but it did! BAM!
Bro you're carrying me through my ML course and exam
Good luck! :)
Thank you Josh! It is so amazing you explained CNN clearly in just 15 minutes :)
BAM! :)
Just to let you know how much I appreciate your quests! Absolutely simple but not missing any concept
Thank you! :)
You are an amazing teacher -- we're lucky to have you.
Thank you!
I was really confused on this concept before I came across this video, now I feel I understand it way better. You really helped a lot! Thank you so much!
Bam! :)
Thanks for this nice video. Got totally pwnd in an interview on this and won't ever be again.
BAM! Good luck! :)
Hands down to the best video and great channel. Thank you for the incredible effort and dedication!
Thank you very much! :)
amazing.....what an effort....the great animations, dynamic graphs and equations, etc. Well done
Thank you so much 😀!
Great video! And would like to ask a question ---- How is the first filter computed by Back propagation (it started with random values in the 3*3 pixels, then it was adjusted by BP). And if i break down the question to sub-questions (a) What loss function is used in this BP. (b) And the gradient used in BP is with respect to who? Thanks again for the great content!
In this specific case, the loss function is the sum of the squared residuals, but cross entropy is much more commonly used in this situation. The gradient is with respect to each parameter we want to estimate (so each square in the convolutional filter, each bias, each weight etc.)
This is the best explanation for CNN you could ever find. wow just wow
Thank you very much! :)
Thank you Josh!!! You truly are the best at explaining these concepts. I would love to see future videos on how to train the kernels, and more on image recognition/computer vision (clearly explained of course). I also got your book and it's really nice, maybe there can be a part 2 in the future 👀
I'm writing a new book all about neural networks right now and hope to have it done soon.
I really enjoyed it; although I'm somewhat familiar with the CNN, bbut the part where pooling basically rewards the match between the filter & the image clicked :]
best,
bam! :)
This was an amazing video! However, I'm a bit confused about how higher complexity neural networks work? From other sources I have read that CNN's can have multiple convolutional layers, but this doesn't make sense to me. If convolution is used to get a general map of features from the input, and you use max pooling to get values which you input into nodes and you calculate weighted sums etc how can you reapply convolution in a further layer?
We can duplicate pretty much everything that happens before the "normal neural network" at the end to add more convolutional layers.
@@statquest What would it mean to add them at the end? Like at the start it makes sense as we are trying to map the features of the input image, but at the end what are you achieving by adding more convolutional layers?
@@bowlteajuicesandlemon You could just create additional inputs to the final fully connected NN. That would allow you to combine the different features you detect with the filters.
Might be a big ask, but I would really appreciate if you released a video on YOLO (You Only Look Once), CNN variant. I love your videos!
I'll keep that in mind.
I have a question.
Can you have more than one filter in order to identify sub patterns?
For example you could want to identify the main sub shapes that make up numbers from 0-10 (circles, lines, diagonals) as another hidden layer before guessing the correct number. Is this actually needed/correct?
Thank you
You can add as many filters as you want. In the video I simply used the simplest example I could come up with.
Thanks for your amazing videos! Could you possibly make a video explaining Graph Neural Networks?
I'll keep that in mind.
Omg！！
Thank you so much for making CNN video. Bammmmm!
Thank you!
"I don't know how much time does Artificial Neural Networks take to train, learn the input data, But you are putting more efforts and it taking much time in your training time".Thanks to your efforts sir.
, your videos really explains very well and it helps us in visualizing easily.
Thank you very much! :)
Hey there, thanks so much for this video! It helped me way more than my university masters degree course material :)
I was just wondering if you were planning on creating videos on the following topics:
- Recurrent Neural Networks
- Transformer Neural Networks
- Graph Convolutional Networks
- Deep Generation Models.
Would be awesome!
Cheers :)
I'll keep those topics in mind.
After watching the unskippable lectures of my professor for hours and understanding nothing, this 15 min viode did wonders, thanks Josh! 😌
Glad it helped!
Thank you very much for this video
5:14 have u had any videos of backpropagation to adjust the filter? It's reaaly hard to imagine that
Not yet.
Amazing videos. I used to watch your videos for study. I insist my students to watch. May I know what is the meaning of your BAM😅
I'm glad you enjoy my videos. To learn more about BAM, check out... th-cam.com/video/i4iUvjsGCMc/w-d-xo.html
Hi Josh, you know you are awesome, you know you and I both are in this domain and I have also started learning to play guitar. I hope this channel will help me in my journey.
BAM! :)
I felt smarter after watching your video!! Always felt dumb during lectures :(
Hooray!!! I'm glad the video was helpful.
This is the best explanation i've checked to many resources but no one simplified that much!
Thank you!
Really helpful! Just a shame that it doesn't have more view :o Subscribed.
Thanks!
Great lecture, thanks a lot.
Help me a lot.
Could you consider a video about reinforcement learning?
Have a great day.
Hopefully soon.
Hey Josh! Thank you so much for this video. This is the best CNN Explanations I have ever seen.
Thank you very much! :)
What a simple way to explain such a complex topic. Perfect explanation Josh.
Thank you very much! :)
@@statquest Thank you so much for making these amazing videos for us Josh. I hope in the near future we get to see how RNN's with LSTM work :)))
Hey, Thanks for the simplified explanation.... it's too good!!
Thank you! :)
Me: spending days trying to understand the topic
Statquest: 15 minutes... take it or leave it!
bam!
All of your videos are amazing. You are very talented to explain complicated things in a simple way. I am looking forward to seeing embedding, attention and transformers videos from your point of view.
Awesome, thank you!
I can't imagine how you can explain so simply ...hats off to your work ..great and superb explanation...need lot of statistical videos like this
Thank you so much 😀
if not this video and you learn the Neural Networks in picture classification in book, you need spend a total afternoon and finally you may feel you are stupid. Now in StatQuest you only need spend half an hour
bam!
Thanks for the awesome content, just loved this neural networks series!
Thank you very much! And thank you for your support!!! :)
CNN's Clearly explained here you are terrific, many thanks.
Many thanks!
The best tutorial as always. Thanks. Looking forward to seeing RNN.
Glad you enjoyed it!
Hear me out, you are the God (of making things simple) in Human Flesh.
Thanks!
Thank you! Thank you! Thank you! Thank you! Thank you! Thank you! Thank you! Thank you! Thank you! Greetings from Brazil! :)
Oi Brasil! Muito obrigado!!! :)
How do we learn the filter through training? Inputs to NN are from pooled matrix and we cannot train inputs.
Backpropagation. The max pool thing is actually pretty easy to handle in that context, but I'll leave the details as an exercise for the reader.
Thumbs up even before starting the video cause I'm sure it's going to be awesome!
Hooray!
Thankyou. Thankyou! You are amazing master of explaining things... break it down to the smallest chunk and and build it up in step by step. I very much look forward for more marching learning tutorial. There is lot of tutorial out there and I spend lot of time understanding it but nothing match the the way you explain. Thank you Tons for awesome contents you have created and the insights you provide
Glad it helped!
And, thanks to Josh that I started saying Baaaam !!! and double Baaaam in my real life :P
BAM! :)
that was awesome. thanks very much Josh. big shout out from brazil
Glad you liked it! Oi Brasil!
I've never seen such a simple yet very good explanation of a CNN. Thanks a lot! As a non-native english speaker I really love the simplicity and the written texts in your videos.
Thank you!
Amazing video! As always, I am incredibly thankful for all the time an effort you put on to these lessons :)
Thank you! :)
such a good explanation, CNNs fry my brain up
Thank you!
What I could make of this video is that once the filter, its bias and are tuned through back-propagation and appropriate activation function is selected, after max pooling its vector is fed into the ordinary neural network which learns to classify whether such kind of matrix could come from X or O.Have i understood correctly..?
Also the max pooled vector/matrix will fill 0s and 1s in relatively unique ways (for X and O) depending upon how the filter has matched to the original image.That forms basis for classification..!!
I believe that is correct.
@@statquest thanks Josh for replying on my comment..!Your series is 'the' best on TH-cam on ML.
This is the most beautiful video on all youtube ! Awesome !
Thank you! :)
besssssssssssttttttttttttttttttttttttttt!!!
Thank you! :)
simply an amazing explanation.
Thank you!
I saw the entire NN series. Thank yoy Josh! BIG BAM!!
Thank you!
so clear explanation. Thank you so much for this lecture.
Glad it was helpful!
Very good video! You are a live-saver. Thanks
Glad it helped!
Awesome explanation. Thank you so much.
Thanks!
I am an MSc student of Data Science. I learn alot here than in Class😅
bam!
I love your videos, I have binge watched your entire machine learning series. One suggestion I might add is the following: It can be confusing to use 1s to represent black pixels and 0s to represent white pixels, because in Computer Vision a black pixel has a value of 0 and a white pixel has a value of 255. So when normalized Black = 0 and White= 1. Thank you so much for these videos btw I love them.
Thanks!
very clear, thank you so much.😁😁😁
You're welcome 😊
Abicim yemin ederim hayatımda bu kadar iyi anlatım gördüğümü sanmıyorum
Bam! :)
Just finished the NN series. If only my highly-cited professor could explain as clearly as you could.
Thank you
bam! I'm glad you like my videos.
te quiero mucho hombre que habla inglés tan claro que se entiende sin problema
de nada! :)
Can I say, Huge BAM!!!
YES! :)
OH MY GODNESS... NOW I KNOW HOW CNN WORKS ... THANKS FROM OPPOSITE SITE OF THE EARTH
BAM! :)
omg u are not a normal human
it's like u open my brain and insert the informations into it and close it
Bam! :)
Now we're getting into the meaty stuff! Lessgoo ❤
bam! :)
Does anyone know the python code for this lesson? To make a code which can classify 'O' or 'X' from a CSV ?
I'm working on that, so stay tuned.
@@statquest Most of who watch your videos are in the Software/AI field, it would be really helpful for beginners like us if you implement the Python code (From scratch, without using external libraries like SciKit learn, Keras or Tensorflow) it would be so much helpful for us. Also, thanks for the effort you put in your videos, my Machine Learning journey is becoming way easier because of your great explanation.
Thank you for helping me and my friends in our journey
Thanks!
I literally binged your neural network videos in a day like a Netflix show and now realized that I am at the end of the series to date and I need to wait for a new episode!
BAM! :)
Hi Josh! First of all let me tell you that your youtube channel is amazing! Thank you for that!
Also, I would like to know if you are going to release any content about 1D Convolutional for Time Series Data?
Have a great week! Thanks!
Not in the immediate future. For time series data, I've been describing RNNs: th-cam.com/video/AsNTP8Kwu80/w-d-xo.html and LSTMs: th-cam.com/video/YCzL96nL7j0/w-d-xo.html
Max Pooling sounds like a good name for a character.
Totally!