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 ...

At version r1.5, Google's open source machine learning and neural network library is more capable, more mature, and easier to learn and use If you looked at TensorFlow as a deep learning framework ...

While you can train simple neural networks with relatively small amounts of training data with TensorFlow, for deep neural networks with large training datasets you really need to use CUDA-capable ...