To learn more about Lightning: github.com/PyTorchLightning/pytorch-lightning To learn more about Grid: www.grid.ai/ Support StatQuest by buying my book The StatQuest Illustrated Guide to Machine Learning or a Study Guide or Merch!!! statquest.org/statquest-store/

@rathnakumarv3956

Жыл бұрын

whether the book include LSTM and RNN for bi variate input time series data as well?

@statquest

Жыл бұрын

@@rathnakumarv3956 Nope, just basic neural networks. My next book on deep learning will have more stuff about fancy neural networks.

@rathnakumarv3956

Жыл бұрын

@@statquest please include CNN, RNN and LSTM for multivariate time series as input and continuous variable as out put - problems, these are very much useful in climate change studies.

@statquest

Жыл бұрын

@Tech What time point, minutes and seconds, is confusing? And have you watched the entire series on Neural Networks before watching this one?

@Lyr00

5 ай бұрын

@statquest I have a question about the vanishing gradient problem. I understand that input1 from the first timestep is having less and less impact on the output the more steps we take but isn’t the gradient also relying on the new inputs of every timestep? I don’t understand why the gradient is vanishing if the new inputs aren’t that heavily discounted as the timesteps that are older. I imagined it’s more like the old inputs are less impactful and the network is more focused on the newer inputs but can still train normally. Is there something I’m missing?

The only place on the internet where you can actually grasp a complex topic before diving deeper into the topic. I am so grateful people like you exist. Thank you!

@statquest

Ай бұрын

Thanks!

I'm in a deep learning class right now and the amount of straight math that my teacher throws at me is overwhelming. Videos like yours are incredible and I'm so thankful for the help and the color coding and the fun that makes it worth watching! It is super helpful as I'm studying for my midterm and just want to get a more definite grasp of what all this math actually means without reading someone's Mathematics PhD dissertation or something

@statquest

6 ай бұрын

Good luck on your midterm! :)

Everytime I watch on of your lessons, I become sooo happy, because you make all the subjects easy to be understood in magical way. Thank you for your effort

@statquest

5 ай бұрын

Wow, thank you!

I'm just in love with your content. I've watched your neural network series and it was just so easy to understand. You really deserve more subs and views Josh!

@statquest

Жыл бұрын

Thank you very much! :)

Josh, I found your channel yesterday and have been binge watching. Incredible work in democratizing knowledge. Thankful for your work.

@statquest

11 ай бұрын

Thank you!

@sylwiagotzman5422

3 ай бұрын

democratizing knowledge -- exactly !!!

Josh!!!! I love u!!! I can't wait to learn about the Transformers!! thank you very much for your content

@statquest

Жыл бұрын

Thank you!

@capyk5455

Жыл бұрын

Josh teaching about transformers would be a blessing

@statquest

Жыл бұрын

@@capyk5455 I'm looking forward to it!

@shaiguitar

Жыл бұрын

Transformers out yet or some ETA to expect?

@statquest

Жыл бұрын

@@shaiguitar LSTMs comes out in the next week or so. Then I'll start working on transformers.

Never quite understood RNNs until I watched this video, thank you! A hand-calculated example of a one-to-one RNN is extremely hard to find online, so this was perfect. The only one out there, I believe.

@statquest

Жыл бұрын

Thanks!

Our lecturer at the uni recommended us this video. I am amazed how simply it is put. Great job! Both funny and informative ❤

@statquest

Күн бұрын

Thank you!

One of the most underrated channels. Never once have I had trouble understanding the intuition of whatever you explain. I'd donate money to you if I weren't a broke college student.

@statquest

Жыл бұрын

Thanks!

Thanks to your series of videos on neural networks, I was able to pass the entrance exam for PhD program at St. Petersburg State University.

@statquest

10 ай бұрын

Congratulations!!! TRIPLE BAM!!! :)

You can't understand how good this is. I've spent all of yesterday trying to understand these concepts but I couldn't grasp them. THANK YOU!!!

@statquest

10 ай бұрын

Glad it helped!

Man, this is awesome. I wasn't understanding anything about RNNs in my course but thanks to this video is all clear now. Thank you Josh Stamer :D

@statquest

Жыл бұрын

BAM! :)

Excellent video as always, professor! I can't wait for a video explaining PARTIAL LEAST SQUARES!!

@statquest

Жыл бұрын

I've got that on the to-do list.

This explanation covers some very important points that were missed in several other lectures I've watched on this subject. Thank you for clearing things up for me.

@charlescoult

Жыл бұрын

For example, the note at 10:31

@statquest

Жыл бұрын

Thank you! Yes, that little detail is important, but often glossed over.

Amazing video as always, professor! I cant wait for the video on LSTM

@statquest

Жыл бұрын

You and me both!

@usamsersultanov689

Жыл бұрын

@@statquest when it comes to application of RNN the LSTM is sometimes a must to have:) that’s why it would be great to have clearly explanation of LSTM. But these are little things. In any case, thank you very much for the valuable knowledge that we can get here.

@statquest

Жыл бұрын

@@usamsersultanov689 I hope to have a video on LSTMs soon.

@james199879

Жыл бұрын

@@statquest One on Transformers and their variations would be even greater :D

@statquest

Жыл бұрын

@@james199879 That's the master plan, but we'll get there one step at a time.

I was looking for a small thing in RNN, but your way of explanation forced me to keep watching the entire video! and I subscribed to your channel!!

@statquest

Жыл бұрын

Hooray! Thank you very much! :)

Very high level explanation. Waiting for the next video on "Long-short Term Networks". Thank you so much.

@statquest

Жыл бұрын

Thanks! :)

They way you explained RNNs made me so excited for LSTMs. Can‘t wait to see it!

@statquest

Жыл бұрын

bam!

Such a great explanation!! Will be watching as many of your other videos as I can while we wait for the next one :))

@statquest

Жыл бұрын

Thank you! 😃

Really looking forward to your LSTM video.. You are a very good teacher !!

@statquest

Жыл бұрын

Thank you!

@WonPeace94

Жыл бұрын

@@statquest when will you make the next vid ? i have exam in two weeks and i need your LSTM video

@statquest

Жыл бұрын

@@WonPeace94 :)

You're gonna carry me through my neural networks class, what a godsend

@statquest

6 ай бұрын

You can do it!

Oh man! This has been super tough for me to wrap my head around. I knew this was going to be a great weekend! Thank you for the drop! :D

@statquest

Жыл бұрын

BAM! :)

Thank you for sharing 🙂 super excited for the transformers statsquest!

@statquest

Жыл бұрын

Thanks!

Your channel should be mandatory for all universities teaching AI 💖

@statquest

11 ай бұрын

Maybe one day!

@guptafamily1981

7 ай бұрын

It will be for sure 😊

This is the CLEAREST explanation of RNNs.

@statquest

Жыл бұрын

Thank you!

Awesome! Thank you, once again, for such a clean and didactic explanation !!

@statquest

Жыл бұрын

Glad you liked it!

U have an amazing way of explaining with adlibs loved it and thank you so much as I was not able to understand at all but now it is very clear

@statquest

Жыл бұрын

Glad I could help!

Hi Josh, You are the best. Nobody has explained exploding gradient like you have, Thank you

@statquest

Жыл бұрын

Wow, thanks!

I like the way how clearly and easily you explain concepts. Thank you very much!

@statquest

3 ай бұрын

You're very welcome!

This was the best explanation I've heard for RNNs!

@statquest

Жыл бұрын

Thank you! :)

With this level of simplicity in teaching, even a high schooler could grasp these concepts, probably quicker than me! Scared of the future now....

@statquest

Ай бұрын

:)

honestly your channel is one of if not the best channel on all youtube, thank you so much for this!

@statquest

Ай бұрын

Wow, thank you!

Amazing, This is one best and coolest learning tutorial i have watched ever, great work Josh, keep it up. Thanks

@statquest

Жыл бұрын

Thanks, will do!

OMG, Finally I understand Vanishing Exploding Gradient, Thank you StatQuest!

@statquest

Жыл бұрын

HOORAY!!! Thanks for supporting StatQuest!!! TRIPLE BAM! :)

Thanks a lot Josh. Every concept explained by you is a BAM!!!!!!!!!!

@statquest

Жыл бұрын

Glad you think so!

12:22 is probably the cutest bam I've heard Also thank you for your videos! They have definitely been helping me get through my Bioinformatics grad course. You are AWESOME

@statquest

Жыл бұрын

Thank you so much and good luck with your course! :)

Dude that DOUBLE BAMM and TRIPLE BAMMM kills me. Actually fun way to get info. Also greate video very easy to understand

@statquest

14 күн бұрын

Thank you! :)

Love the little embarrassing singings during the videos. Subscribed. Great videos!

@statquest

5 ай бұрын

Thanks!

Thank you for this amazing explanation! Waiting for the video on LSTM! :)

@statquest

Жыл бұрын

Coming soon!

literally before I see your video, I made a like, that much I trust your information and knowledge , thank you for your time and effort to explain this to us

@statquest

Жыл бұрын

Thanks!

Beautiful and succinct explanations!! So glad I found your channel....lots of love

@statquest

5 ай бұрын

Thanks!

you definitely are the best teacher for machine learning and deep learning

@statquest

Жыл бұрын

Thank you!

That intro was sick. I smashed like button immediatelly :D

@statquest

Жыл бұрын

bam! :)

KA-BAAAM! Thank you for all these amazing videos. I wish you had different series about CNNs and RNNs separately.

@statquest

Жыл бұрын

If you want to learn about CNNs, see: kzread.info/dash/bejne/enurpLp9e6nRaaw.html

@sinarokhideh6794

Жыл бұрын

@@statquest How could I not have seen this?! By different series, I mean it would be great if you could create more videos covering each of these topics in more detail. But of course, you've already done so far, and I'm so grateful to you for sharing your knowledge in such a good way.

Thank you so much 😭 People like you are the real mvp of humanity !

@statquest

Жыл бұрын

Thanks!

Very hyped for the video transformers ! Keep up the good work, it's amazing how good it is!

@statquest

Жыл бұрын

Thanks!

You are insane Man, very clear and understandable explaination!! Thanks a ton 🎉

@statquest

4 ай бұрын

Happy to help!

Clearly explained the difference between RNN and normal network, gradient vanishing/exploding! Looking forward to the LSTM and Transformer videos!!!

@statquest

Жыл бұрын

Thanks!

Josh, you are the person who make ML theory so understandable!

@statquest

2 ай бұрын

Thank you!

Best explanation I've seen from RNNs. Thanks.

@statquest

Жыл бұрын

Thank you!

Thank YOUUU Clearly explained !! I have been struggling with it !

@statquest

Жыл бұрын

BAM! :)

I saw a light turning on my head! great video

@statquest

11 ай бұрын

bam! :)

Muchas gracias por traducirlo, es un muy buen material❤

@statquest

7 ай бұрын

De nada!!! :)

Can’t believe I was working with a NLP problem at my job using LSTMS and then you just published a video about RNNs. You’re a lifesaver! By the way, would you consider doing a SOM or a Boltzmann Machine algorithm video in the future? Love from Brazil

@statquest

Жыл бұрын

I'll keep those topics in mind.

Very impressive video! I always explain concepts in a simple way. Could you make more videos about deep learning?

@statquest

Жыл бұрын

I'm working on them as fast as I can.

Oh man i literally watch his videos like a web series its very fun and very easy to understand thank you very much sir !!!!😭😭

@statquest

4 ай бұрын

Thanks!

Im a simple man, I see statquest, I click like. Can't wait for the videos on transformers.

@statquest

Жыл бұрын

bam! :)

Any darn fool can make something complex; it takes a genius to make something simple (" Albert Einstein"), and you made it very very simple. Thanks!

@statquest

Ай бұрын

Thank you very much! :)

Great Video! I was struggling to understand math's behind vanishing and exploding gradient in detail and the points that you shared in the video are definitely useful. Could you please point to any additional articles which explain the math's in more detail. Thanks!

@statquest

Жыл бұрын

Look into "Backpropagation through time".

Really liked the video. Quite creative and straight to the point!

@statquest

2 ай бұрын

Thanks!

Hi Josh! Ty for video it was really helpful but i still have one question. In the class teacher said that hiden layer and input value are multiplied by matricies, in your example it was scalars. So how your example would change if i still want to predict stock price?

@statquest

8 ай бұрын

Internally, neural networks do the math using matrix algebra because it is efficient to code it that way. However, matrix algebra is just multiplying things by scalars and then adding them up, which is what we do here.

@statquest

8 ай бұрын

That said, I hope to create a video that shows, exactly, how the diagrams I draw are related to matrix algebra.

You don’t understand how good the timing of this is. Been struggling to explain the concept in detail on my MSc project. Are you are doing a video on LSTM / GRU soon ??

@statquest

Жыл бұрын

Yes, I hope so.

i come to listen to " peep poop poop"

@statquest

Ай бұрын

bam! :)

True Hero. I have an exam on 29th about rnns, lstms and transformers.

@statquest

Жыл бұрын

Good luck! :)

Great work ! I would like if you make more videos about the encoder-decoder parts of the network as well as integrating attention modules into RNN's

@statquest

Жыл бұрын

I'm working on those.

Excelente proyecto! no pense que con dibujos fuera tan entretenido e informativo. Definitivamente un muy buen video para comenzar!

@statquest

7 ай бұрын

Muchas gracias! :)

Thank you for making these videos! They are very helpful.

@statquest

2 ай бұрын

TRIPLE BAM!!! Thank you so much for supporting StatQuest!!! :)

Clear as day!!! Hooray!!!! Thank you Josh

@statquest

Ай бұрын

Thank you!

Amazing explaination with simple, easy-absorb, attractive method and but still pursue clear concept. 🙂 Kabaam... nice job

@statquest

Жыл бұрын

Thank you! :)

Omg, that intro jingle is gold!

@statquest

7 ай бұрын

bam!

To learn more about Lightning: github.com/PyTorchLightning/pytorch-lightning To learn more about Grid: www.grid.ai/ Support StatQuest by buying The StatQuest Illustrated Guide to Machine Learning!!! PDF - statquest.gumroad.com/l/wvtmc Paperback - www.amazon.com/dp/B09ZCKR4H6 Kindle eBook - www.amazon.com/dp/B09ZG79HXC English This video has been dubbed using an artificial voice via aloud.area120.google.com to increase accessibility. You can change the audio track language in the Settings menu. Spanish Este video ha sido doblado al español con voz artificial con aloud.area120.google.com para aumentar la accesibilidad. Puede cambiar el idioma de la pista de audio en el menú Configuración. Portuguese Este vídeo foi dublado para o português usando uma voz artificial via aloud.area120.google.com para melhorar sua acessibilidade. Você pode alterar o idioma do áudio no menu Configurações.

Your book on Machine Learning was excellent. I am looking forward to reading your book on deep learning.

@statquest

Жыл бұрын

Thank you very much!

Hi Josh. First of all, I really appreciate your videos. None has ever explained this much clearly and easily. I will watch all of yours in a week. The sad news is that LSTM is closely related to my Master's project for computational cognitive neuroscience. Can't wait your LSTM videos 😢. Can you tell me when your LSTM video will be posted? Or at least, can you recommend resources to understand LSTM? Does "The StatQuest Illustrated Guide to Machine Learning" have contents of RNN and LSTM or just plain neural networks?

@statquest

Жыл бұрын

LSTM should be out in a few weeks. Unfortunately the book does not cover them.

Those tones won won bam double bam kaboom n d fun way of learning, opens up mind for grasping things real quick as well as we can think freely wdout bcming nervous. U lord🙌

@statquest

Ай бұрын

Thanks!

Hey, hopefully this will safe my Deep Learning exam. And... love the sound effects.

@statquest

3 ай бұрын

Best of luck!

Thanks so much, sir for such useful content. Huge Respect!

@statquest

7 ай бұрын

Thank you!

You graced upon us as a stats saviour :))) Send love from Australia

@statquest

7 ай бұрын

Awesome! Thank you!

Awesome video series, very helpful. Thanks Josh

@statquest

8 ай бұрын

Glad it was helpful!

... you sir are a timeless legend!

@statquest

7 ай бұрын

Thanks!

Great video!! I can't wait for LSTM and transformer videos!

@statquest

Жыл бұрын

Coming soon!

OMG I love you for your teaching style

@statquest

Жыл бұрын

Thank you! 😃

Having a "clearly explained" episode on Attention model could be interesting. There's a paper called "attention is all you need". I had an impression that attention model is somewhat equivalent to LSTM and RNN without looking back, but never grasped the details

@statquest

Жыл бұрын

I hope to cover attention soon.

@axelanderson2030

Жыл бұрын

@@statquest I hope you do to

Hi Josh! thank you for another great explanation. Just crossing my fingers you explain time series (ARIMA/SARIMA...) soon 😊

@statquest

Жыл бұрын

I'll keep that in mind.

Your videos are wonderful love your humor ! :)

@statquest

Жыл бұрын

Thank you so much!

Thank you for the video. I believe it was a clear explanation.

@statquest

6 ай бұрын

Glad it was helpful!

the vanishing/exploding gradient problem is synonymous to choosing a right value for alpha (learning rate) as choosing a greater value would leave us bouncing and choosing a lower value would lead to more iterations of gradient descent

@statquest

4 ай бұрын

Nice

You're the best, thanks from the heart❤

@statquest

Жыл бұрын

Thank you! :)

you are vry very very very very very brilliant teacher ! you are my low variance and low bias position.

@statquest

10 ай бұрын

bam! :)

Very well explained, I’ll go watch the rest! Kaboom!

@statquest

10 ай бұрын

Thanks!

Thank you so much. You make great videos... Just great teaching. Thanks alot.

@statquest

9 ай бұрын

Glad you like them!

Can RNN's be used for data that depends on multiple variables not just time (such as lateral, vertical, etc forces) and outputs a sequential output such as layup pattern angles for a composite material like (90, 45U, 90W, 45, etc)?

@statquest

9 ай бұрын

Presumably, or they can be combined with neural networks that can.

@AG-cx1ug

8 ай бұрын

Thanks for the response! @@statquest

So looking forward to the LSTM video!

@statquest

Жыл бұрын

SOON! :)

Thank you for the fantastic explanation and amazing content. Your videos help me a lot with my course and research work. I'm wondering why do we have a non-convex loss function in the vanishing/exploding gradient problem?

@statquest

Жыл бұрын

It's not that the loss is non-convex, it's that the gradient is either too large or too small.

why are you master of everything???? I have been watching your video for two years through out my university course

@statquest

8 ай бұрын

Ha! Thank you! :)

Perhaps the gradient could be calculated in log-space. Somewhat related: log-space is also commonly preferred for price data in quantitative finance

@statquest

Жыл бұрын

Interesting idea!

Almost finished with the NN series; would like to see a video about hidden markov model one day :-).

@statquest

Жыл бұрын

I'll keep that in mind.

Man! You're the best youtuber over the world! My total respect for you! Have you ever thought showing us here a python code RNN and LSTM NN :D?

@statquest

Жыл бұрын

Thanks! We might use Lightning for LSTM and Transformers.

I wish you were my math teacher! The whole class would have sang like you while calculating🤣

@statquest

Жыл бұрын

That would be awesome!

Josh, you are amazing! Thank God you exist

@statquest

Жыл бұрын

Thank you!