Deep Learning in Practice: A Hands-On Introduction Using PyTorch
Intended Audience: Anyone who wishes to learn how to create deep learning systems using PyTorch, the de facto library for modern machine learning and AI.
Knowledge Level: Basic knowledge of machine learning terminology. Minimal programming experience with a C-family language such as Python, C/C++, C# or Java is helpful but not required.
Workshop Description
This one-day introductory workshop dives deep. You will explore deep neural systems, including regression, binary classification, and multi-class classification. It’s a hands-on class; you’ll learn to implement and understand PyTorch deep neural networks as well as unsupervised techniques. Just as importantly, you’ll learn exactly what types of problems are appropriate for deep learning techniques, and what types of problems are not well suited to deep learning.
Instructor James McCaffrey oversees Microsoft Research’s initiative to transfer deep learning intelligence into all products, services, and supporting systems across the enterprise. Workshop participants will access much of the same state-of-the-art training material used for this work at Microsoft. Along the way, James will cover case studies detailing large-scale deployments for their internal clients that have generated astounding ROIs.
Workshop attendees will gain the following practical hands-on experience:
- How to prepare, normalize, and encode data for deep learning systems.
- How to install the PyTorch deep learning library on a local machine, and how to use online systems such as Google Colab.
- How to run and interpret PyTorch deep learning systems.
This workshop assumes you have a basic knowledge of machine learning terminology but does not assume you are a machine learning expert. Some theory will be presented but only enough to help you understand how to make a practical, working deep learning system. This is a code-based workshop, so some programming experience will be helpful. However, beginners will be able to follow along but may have to work a bit harder to keep up. In previous editions of this workshop, some attendees have opted to follow along with the instructor rather than engage with the code demos.
Hardware: Bring Your Own Laptop
Important note: Each workshop participant should bring their own laptop running Windows 10/11 or MacOS. Attendees must have administrator privileges on their machine (i.e., no company laptop restrictions, and be able to access and save workshop information via a flash drive), and be able to connect to the Internet.
Workshop attendees are not absolutely required to have a laptop, however, having a laptop which allows hands-on experimentation will provide a better experience for most attendees.
Attendees receive an electronic copy of the course materials and related code at the conclusion of the workshop.
Instructor
James McCaffrey, Senior Scientist Engineer, Microsoft Research
James McCaffrey works for Microsoft Research in Redmond, Wash. James explores applied deep machine learning and AI. James has a PhD in cognitive psychology and computational statistics from the University of Southern California, a BA in psychology, a BA in applied mathematics, and an MS in computer science. James learned to speak to the public while working at Disneyland as a college student, and he can still recite the entire Jungle Cruise ride narration from memory.