It's possible to create neural networks from raw code. But there are many code libraries you can use to speed up the process. These libraries include Microsoft CNTK, Google TensorFlow, Theano, PyTorch ...

Keras is a code library that provides a relatively easy-to-use Python language interface to the relatively difficult-to-use TensorFlow library. Installing Keras involves three main steps.

Google announced TensorFlow 2.0 is now available for public use. The alpha version of the deep learning library made its debut this spring.

Full rewrite of the deep neural network API supports Keras workflows on top of the three leading machine learning frameworks.