Initially started as a Pythonic version of "Hacker's guide to Neural Networks" by Andrej Karpathy.
Motivated me to build a Library to learn and code neural networks for deep learning.
There are plenty of amazing libraries out there. But, I felt there is a strong need for beginners to really understand
neural networks well and know what's going on in each neuron, before they dive deep into Deep Learning. Afterall, not everything is a Black-box.
Regarding the library, I wish to create just single layer of abstraction - front-end (interface) and back-end (engine)
- The Interface is intended to be easy-to-use, with a Keras like functionality.
- The engine is easy-to-understand, programmed as how various components of the Neu-Net machinery function.
Also, the 'Neu' part refers to both, 'Neural' as well as 'Newbies' (or Noobs) to Machine Learning.
Demo and supporting blog -- coming soon.