========
PyTorch
========

PyTorch is one of the most popular deep learning libraries currently
available, and it lets us implement neural networks (NNs) much more efficiently than any of our
previous NumPy implementations.

Parallelizing neutral network training
======================================

Installing PyTorch

.. console::

   $ pip install torch==1.9.0 torchvision==0.10.0

You can verify your PyTorch version from your terminal, as follows:

.. console::

   $ python -c 'import torch; print(torch._version_)'

Next, we focus on PyTorch as a library for implementing deep neural networks. What is a Neural Network?

.. image:: _images/neutral_network.png
   :alt: Neutral Network Image
   :align: center

If you don't have access to a GPU, there are several cloud computing providers such as `Kaggle`_

.. _Kaggle: https://www.kaggle.com/code

.. image:: _images/kaggle.png
   :alt: Kaggle Image
   :align: center


The mechanics of PyTorch
================================


Classifying images with deap convolutional neural networks
==========================================================

Modeling sequential data using recurrent neural networks
========================================================

Improving natural language processing 
=====================================

Generative adversarial networks for synthesizing new data
=========================================================

Graph neutral networks for capturing dependencies
=================================================

Reinforcement learning
======================