dailyemchat | Неотсортированное

Telegram-канал dailyemchat - Daily Moron Chat

244

Discuss philosophy, ideology, religion, etc. Strong language is allowed. Don't be a moron, respect others (unless they are too dumb). Created and supported by @dailyEm and @egorcentric

Подписаться на канал

Daily Moron Chat

Who is owner of this group

Читать полностью…

Daily Moron Chat

Maybe they saw the future profits they'd be sitting on and realized walking away would be a massive loss? Sam hyped up AGI/ASI and its possibilitiess

Читать полностью…

Daily Moron Chat

Naa, not rly. But they have weird practices and shifted to for-profit

Читать полностью…

Daily Moron Chat

Basically they scamming?

Читать полностью…

Daily Moron Chat

https://youtu.be/WLQkSmyW5rE?si=UVh4oFwjLEkWk8OH

Читать полностью…

Daily Moron Chat

If I make a joke will you offend

Читать полностью…

Daily Moron Chat

if you need a good base, refer these videos: https://www.youtube.com/playlist?list=PL5-TkQAfAZFbzxjBHtzdVCWE0Zbhomg7r

this prof taught me well 🙏

Читать полностью…

Daily Moron Chat

But the neural network

Читать полностью…

Daily Moron Chat

similar to what u did here

Читать полностью…

Daily Moron Chat

Gradient are basically the changes that are supposed to be made to the following vairbles right

Читать полностью…

Daily Moron Chat

yeah for sure! just do a simple network and you will understand

Читать полностью…

Daily Moron Chat

that's done thru gradient descent, so need to propagate (or send) those gradients all the way from y to each of these variables

Читать полностью…

Daily Moron Chat

But like we can understand right how it's done

Читать полностью…

Daily Moron Chat

so autodiff is a way to propagate gradients in your weight update step from the output all the way back to the gradients

Читать полностью…

Daily Moron Chat

I used the call back that slows down the learning rate to monitor the loss

Читать полностью…

Daily Moron Chat

Are you interested online work

Dm me

Читать полностью…

Daily Moron Chat

RIP my student. Hope you will reach the depths of deep learning, nice knowing you!

Читать полностью…

Daily Moron Chat

Oh wow she deleted her acc

Читать полностью…

Daily Moron Chat

https://www.openaifiles.org/

Читать полностью…

Daily Moron Chat

You'll die sooner than me

Читать полностью…

Daily Moron Chat

I think someone send me the Cnn video yesterday

Читать полностью…

Daily Moron Chat

So what formula and stuff

Читать полностью…

Daily Moron Chat

Like today I was learning linear algebra and it was related to the vectors and stuff so I got a little deep and figured out the regression formulas and stuff

Читать полностью…

Daily Moron Chat

But like how will I do it

Читать полностью…

Daily Moron Chat

start with a single layer in matrix form

Читать полностью…

Daily Moron Chat

gradient descent basically

Читать полностью…

Daily Moron Chat

for e.g., you need to update theta10,11,20,21,30,21 and phi 0,1,2,3

to update these 10 variables, you need to send the information of the output (i.e. in which way to change these vars so the output aligns with true_value).

Читать полностью…

Daily Moron Chat

naa, that's why we use computers ;d

Читать полностью…

Daily Moron Chat

and when your network gains depth, it becomes even more complicated

Читать полностью…

Daily Moron Chat

I'd say we need to make that one guy fall flat on his teeth so go for accuracy

Читать полностью…
Подписаться на канал