by Goku Mohandas, Alfredo Canziani | Released February 2018 | ISBN: 9781491989937

What is this video about, and why is it important?This video will serve as an introduction to PyTorch, a dynamic, deep learning framework in Python. In this video, you will learn to create simple neural networks, which are the backbone of artificial intelligence. We will start with fundamental concepts of deep learning (including feed forward networks, back-propagation, loss functions, etc.) and then dive into using PyTorch tensors to easily create our networks. Finally, we will CUDA render our code in order to be GPU-compatible for even faster model training.What you'll learn—and how you can apply itDeep learning basics and you can apply it to your domain (X + AI)PyTorch platform basics and you can apply it to any deep learning problemCUDA rendering, which will allow you to train your networks very quicklyThis video is for you because…You may be an experienced AI researcher (academia or industry) with years of experience, and may have coded in platforms such as TensorFlow and Theano before, but may be a bit hesitant to transition into PyTorch. This introductory video will show you how easy it is to switch and the benefits you will reap with PyTorch's dynamic nature.You may also be a software engineer or computer science student or enthusiast looking to get started with deep learning. For you, PyTorch is the best platform to start with because of its simple, yet powerful interface. It makes implementing deep networks very transparent, which allows you to validate all the mathematical concepts you are learning. Familiarity with basic deep learning concepts is preferred but not required as we will cover the math behind the code as well.Prerequisites:An understanding of algebra and basic calculusBasic python skills (knowledge of functions, classes, etc.)Materials or downloads needed in advance:Download and install PyTorch (Instructions provided in the forthcoming GitHub repo)Download corresponding Jupyter notebooks via forthcoming GitHub repo Show and hide more Publisher Resources Download Example Code

1. Introduction to PyTorch 00:00:33
2. Introduction to Deep Learning 00:06:06
3. What is PyTorch? 00:03:52
4. PyTorch Operations 00:07:59
5. Setting up a Classification Problem 00:06:34
6. Data Representation and Structure: Math 00:04:59
7. Data Representation and Structure: Code 00:03:02
8. Math behind Feed Forward Networks 00:07:16
9. Training a Neural Network for Classification: Softmax 00:05:40
10. Training a Neural Network for Classification: Cross-Entropy 00:06:24
11. Training a Neural Network for Classification: Back-Propagation 00:10:24
12. Creating Custom PyTorch Components 00:13:09
13. Proper Training Procedure for Neural Networks 00:10:19
14. PyTorch Basics Wrap Up 00:00:43
Show and hide more