Click here to Skip to main content
15,881,092 members
Please Sign up or sign in to vote.
1.00/5 (1 vote)
How can I create a neural network (textgenrnn)? Is there a detailed tutorial: steps, programs etc? I don't understand GitHub post.?

What I have tried:

I've just read some posts and watched videos. But I don't understand. I'm Russian.
Posted
Updated 25-Jan-20 2:00am

Here you can find books: https://www.slant.co/topics/3747/~books-on-neural-networks[^]
But you probably first need to learn the English language :)

Another idea is to read this in your browser and translate it with Google translate: https://towardsdatascience.com/first-neural-network-for-beginners-explained-with-code-4cfd37e06eaf[^]

More information here: websites-to-learn-about-neural-networks[^]
 
Share this answer
 
v2
Comments
Kebaboo 25-Jan-20 4:15am    
Thank you! Do these books have instructions?

I learn English, I'm intermediate. :)
RickZeeland 25-Jan-20 4:18am    
I only found the link, never read one of these books, sorry :)
I will update the solution with some other interesting information.
My personal favortite:
Neural networks and deep learning[^]
I worked through his whole article and my Feeling is, he does describe everything very simple and very good.

Give it a Trial. To understand it you should know what Derivate of a function means and at least you should have an Imagination what partial derivatives are.

Don't be afraid from the formulas he explains. Most of them are really easy to understand - even I was able to understand them... but it took some time and discipline.

I started with Zero knowledge and end with "my" c# implementation of his example of OCR... and was very impressed "how easy" such a big Task like OCR can be solved ;)

There is also a very helpfull specific article in CP about ANN.
Not 100% sure it must have been this: Neural Networks on C#[^]. It is maybe not an efficient implementation, but what I rememeber it is something General/univerisal.

Good luck.
 
Share this answer
 

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)



CodeProject, 20 Bay Street, 11th Floor Toronto, Ontario, Canada M5J 2N8 +1 (416) 849-8900