And maybe they are...

But Tensforflow is still cool.

Actually, Keras is better.

Or easier at least.

I trained a neural network with just three layers to an accuracy of 96% on the MNIST dataset.

I think it took 5 minutes on my laptop.

I also put peanut butter on my nose.

/thread

a neural network is basically a self-improving AI?

@Deleted User

It's like a structure for statistical learning.

You have weights that determine how strong each neuron contributes.

(((statistical learning))) what the hell

>Whoa, no one said these Central Americans were going to live in MY city!

Each neuron is basically a function of its inputs from the previous layer.

Then you look at how far your output is from the intended result.

women literally unable to think in general principles, only about what is right in front of them, the image

You can then use gradient descent or another error estimation method to back propagate the changes through your neural network.

wow

Common activation functions are sigmoid, tanh, RELU, identity function, and extended sigmoid.

i gotta get in this shit one day, to busy rn tho

That's the neat part: it's easy with tensforflow.

Look at my source. It's only 50 lines.

the fuck? only 50?

You can train it on other things, too. I have a neural network trained to recognize bots on Minds.

and it's not polished code?

Because I hate those thot accounts that are just spam.

They all impersonate Vietnamese women, but they have a certain naming and posting pattern, so I trained a neural network to recognize real users and bots.

Nothing polished.

I suck at JavaScript.

that's amazing

You can also use Python. That's what most people use for AI these days.

@TrunksBish <:think_madpepe:378717098630971395> flower?

The team for the Even Horizon Telescope used Python, too.

And they used one of the FFT libraries a friend of mine worked on.

I have a video creating some better images.

nah i work with JS, nodeJS, learning c++ right now (well not right now, i got school to take care of then back to coding hobby) i tried C but soo little guides it's cancer to study,

The left is the original. The right ones are tweaks I made to the algorithm.

C is hard.

But you need to know at least one language like that.

One that is unmanaged and close to the hardware.