Learn Neural Networks With Go - Not Math! by Ellen Korbes

preview_player
Показать описание
It’s common for even the most amazing programmers to not have the first clue about math. That makes learning neural networks particularly inaccessible, as an integral part of explaining it relies on mathematical formulas. Ah, the formulas… with all their lines and curves and ancient symbols, they are just as unintelligible as they are beautiful.

What’s a better way for us to learn it instead? With a language we all speak: code!

In this talk we’ll look at every component required to write a neural network from scratch. Things like network structure, activation functions, forward propagation, gradient descent, and backpropagation. We’ll look at them as programmers: we define what we’re trying to achieve, then write an implementation for it.

We’ll do that with no specialized libraries like Tensorflow and PyTorch—only Go code. So if you ever wanted to really understand how a neural network works, but thought it to be out of your reach because of the math, this talk is for you.

Code, not math! Algorithms, not logarithms!
Рекомендации по теме
Комментарии
Автор

3:20

I see neurons as a political system or like a project leader. All inputs are the people giving their opinion. The project leader should weigh the inputs an will create a response based on these inputd.

maaikevreugdemaker
Автор

What IDE was the presenter using? Looks awesome!

andreypanin
Автор

Go (programming language) or (board game, weiqi, baduk)?

vegahimsa