Tutorial: Deep Learning in PyTorch

This Blogpost Will Cover:

  • Part 1: PyTorch Installation
  • Part 2: Matrices and Linear Algebra in PyTorch
  • Part 3: Building a Feedforward Network (starting with a familiar one)
  • Part 4: The State of PyTorch

Pre-Requisite Knowledge:

  • Simple Feedforward Neural Networks (Tutorial)
  • Basic Gradient Descent (Tutorial)

Torch is one of the most popular Deep Learning frameworks in the world, dominating much of the research community for the past few years (only recently being rivaled by major Google sponsored frameworks Tensorflow and Keras). Perhaps its only drawback to new users has been the fact that it requires one to know Lua, a language that used to be very uncommon in the Machine Learning community. Even today, this barrier to entry can seem a bit much for many new to the field, who are already in the midst of learning a tremendous amount, much less a completely new programming language.

However, thanks to the wonderful and billiant Hugh Perkins, Torch recently got a new face, PyTorch… and it’s much more accessible to the python hacker turned Deep Learning Extraordinare than it’s Luariffic cousin. I have a passion for tools that make Deep Learning accessible, and so I’d like to lay out a short “Unofficial Startup Guide” for those of you interested in taking it for a spin.