cool video! You may check the example that I have done in my channel to visualize training, learning, gradients and activations.

people in 2024

been following this series in typescript. I must say its a masterpiece. The fact that I was able to write a neuro network from scratch is incredible. Looking forward to follow up videos. And if there are non to follow this is job well done. Greetings from Tanzania

Just bought hardcover. You're a legend for these videos 🫡

Thanks, it works, I am using this script to stay AFK without getting kicked from the session

Hi! Can you share what hardware were you operating on?

The year is 2024 and I am using github copilot on pycharm and its suggesting the same values you are typing.

Hey, are you kidnapped or abducted by aliens? It's been 2 years, and no follow-up.

would love to see the python from scratch series finish

Very useful

Thanks for your tutorial series.

if you could do a tutorial on fine tunning the new version of it thank you for your videos <3

Looks like I can't order the book. Why?

Ay ay ay you procured reduce out of nowhere, how did that happen?

better explained

Anyone know how to change pack to place, when I swap all the packs for place() and enter coordinates and run it, it just comes up blank

can u suggest me some other videos/chanels also sharing about RL like this. This is the most funny and easy to understand video i have ever watched

I firmly believe that the first sentient AI will be born in a home lab like these and not in corporate or federal supercomputers

print("Thanks")

16:41 why adding biases here result in the addition with respective elements in list meanwhile adding 2 lists result in both list getting merged

bro why are you using IDLE of all things you have the option of using?

GREAT TEACHER, GREAT TUTORIAL!

hehe foward xD

NOOO WHERE DID THE CAPTIONS GO?!!?! BRING THEM BACK!!! I AM DYSLEXIC AND NEED THEM!! Dx

How long did it take to create the model

Thx

Your videos are super informational and easy to understand. This saved me a lot of heartache in the process. Thank you so much 👍

what is u transpose inputs instead? and what would happen if you put the transpose weight matrix first in the dot product?

Never felt softmax fn being explained this so easily! Thanks sentdex

Please post the next video sentdex! Please!!

I've just finished watching all 9 of the videos currently on this playlist. I absolutely cannot wait for part 10. PLEASE CONTINUE.

Back again 3 years later, with a little more math under my belt. Very much hoping that you will continue posting videos in this series

Bought the book, would love to see more videos, would be happy to pay for a video course

Why are we making individual classes for the different activation functions? Shouldn't these just be methods of the layers which have them?

how much does that full thing cost ?

Just stumbled across this vid. You’re so young here in your KZbin career. Haha

I'm very thankful for this series, I just learn so much new thing, because you're so good in explaining, and there yet 5 videos to watch!

I have a question. Why does TensorFlow Object Detection (TFOD) use steps? Also, what is the difference between steps and epochs? Why do steps tend to be in the tens of thousands, while epochs usually only reach the hundreds?

What a great explanation man, really appreciate the edit and teaching. Thanks for teaching this much clearly.

i cant believe i found it just now.

This is one of the best series on AI ever!!!

Dude!!! I am on video 4 so far. Thus far you are about 99 out of 100 fantastic. Here is what is missing from my perspective of not knowing what or how to build a NN. Your video series starts out with an expectation of programming in some language and that is totally fair, else none would understand anything at all. I do feel that one would need to have a basic understanding of Python mostly because of terminology. To know that a list is an array and batch is simply an array of arrays and such is useful especially if the student's background is in PHP or Javascript. Now here is where I start exploring outside of your videos.... Your start with the raw code of this NN is also fantastic. What I recommend is a bit more basis explanation. For example what is a layer? Why is a layer? You can mention the function or purpose of weights and also mention that they are or can be random as the "learning" part will be the machine testing different weights and biases in itself. You start out also comparing the code to a NN diagram and that is MOST AWESOME, thank you. You also start out with building this code around a scenario of mainboard/case/rack sensors used to determine the failure of a server. So you basically should have a final result of yes/no it will fail. The same as your cat/dog. But one may assume that humanly we are inputing only pics of cat or dog, thus your output can be a binary of isCat and that is all that is required. I would like to see more in line analogies to your sensor scenario as it is a massive benefit to understanding each element of the NN. That is my only advice. Thus far I love it. When these explanations are missing, it is easy to go outside to another resource and ask what a "layer" is and why or what it does, but from a product perspective "your video series" your intent should be to keep me from venturing out as with a bounce rate, you do not want to lose my attention.

Hi , I can understand how the no. of Biases are calculated. May I know how exactly Weights (in terms of numbers) are calculated?

limit n->infinity Thanks

Hi, how to do it for geopandas? is it same?

Has anyone been able to install the library with pip as he shown ? I keep getting errors like - Preparing metadata (pyproject.toml): finished with status 'error' :')

i know this is an old video but the logic still works, now the question is , if i want to make this public (connection with different network) then how the connection will work

Hello dear I am in Afghanistan how can I provide this details in Afghanistan is not exisr

My model can't load, help plz 🥲🙏 It didn't save it in ".model" format so I used ".keras" as told in exception. And when I try to load it with full path it can't find it... I tried to do smth with path string (like replacing slashes with back slashes and wise versa), but it didn't help. Exception said to make sure that is .keras zip file, so I tried to make folder with model a zip, but it didn't help either... UPD: I found a way to make it find, but now it throws an Exception that says that Sequential model couldn't be deserialized properly(( This is "Hello, World" of CNNs, how tf it takes so much effort to make it work?(((

How I get these Jarvis files dude😊