Only-Numpy

Implementing varity of Neural Network Algorithms only using Numpy Library, and maybe Sklearn (only to generate training data.)

** I MOVED THIS REPO TO GITLAB https://gitlab.com/jae.duk.seo/Only_Numpy

For more tutorial Visit my website: https://jaedukseo.me/.
For more tutorial Visit my You Tube Channel: https://www.youtube.com/c/JaeDukSeo.
Also, Follow me on Twitter: https://twitter.com/JaeDukSeo.
Also, Follow me on Medium: https://medium.com/@SeoJaeDuk.

What's included?

** I MOVE TO GITLAB : https://gitlab.com/jae.duk.seo/Only_Numpy

• ANN Basic And Gate
• ANN Basic Constant Learning Rate
• ANN Basic Constant Step Decay
• RNN without Activation Function
• RNN with Activation Function
• Sythentic Gradient
• Sythentic Gradient (Multi Threaded)

Youtube Channel

• I have a Youtube channel where I try to explain things follow this Link
  

Medium Explanation Posts

Only Numpy: Deriving Forward feed and Back Propagation in Synthetic Gradient (Decoupled Neural Interfaces) with Interactive Code feat. iamtrask

Only Numpy: Vanilla Recurrent Neural Network Deriving Back propagation Through Time Practice

Setting up

Clone the repo

$ git clone https://github.com/JaeDukSeo/Only_Numpy_Basic
$ cd Only_Numpy_Basic

Choose the NN type you wish to run and go into repo

$ cd 2_Decoupled_Neural_Network

run the code in ptyhon3

$ python3 1_Red_Box_Case

License

MIT License