Presented By
O’Reilly + Intel AI
Put AI to Work
April 15-18, 2019
New York, NY

Getting started with PyTorch

Mo Patel (Independent)
9:00am12:30pm Tuesday, April 16, 2019
Implementing AI
Location: Mercury Rotunda
Secondary topics:  Deep Learning and Machine Learning tools

Who is this presentation for?

Data scientists and application developers



Prerequisite knowledge

- General familiarity with Computer Vision terms and concepts - Familiarity with Python coding - Familiarity with Machine Learning

Materials or downloads needed in advance

Although it is recommended that no code is run during the tutorial since the goal is to learn rather than execute code without learning. For those interested, please install latest version of Jupyter Notebook and PyTorch.

What you'll learn

- Understand Computer Vision using Deep Learning - Understand PyTorch - Understand Image Classification, Object Detection & Instance Segmentation - Understand bringing PyTorch models to production


Since it’s arrival in January 2017, PyTorch has captured the minds of Machine Learning researchers and developers. Now two years later, PyTorch has matured into production-ready Machine Learning framework with ever-growing examples, use cases and applications supported by a robust community. Similarly, Machine Learning and it’s subdiscipline Deep Learning has gained immense popularity closely linked to the availability of libraries such as PyTorch and promising results across domains such as Computer Vision and Natural Language Understanding.

In this tutorial, you will learn PyTorch via several examples. As we learn PyTorch, we will implement use cases such as image classification, text classification, and regression modeling. We will do hands-on exploration with transfer learning, working with training and test datasets and learn about taking PyTorch models to production.

Prerequisite knowledge:
Familiarity with Python language and knowledge of machine learning terms and concepts.

Materials or downloads needed in advance:
Notebooks for PyTorch labs will be available a week prior to the tutorial session. At that time (1 week prior to tutorial), we will provide an update on the availability of a cloud-based lab environment or instructions to prepare your own docker based lab environment.

What you’ll learn:
- PyTorch concepts
- How to build machine learning models in PyTorch
- Image Classification, Text Classification and Linear modeling
- Transfer learning
- Working with datasets in PyTorch for machine learning

Photo of Mo Patel

Mo Patel


Mo Patel is an independent deep learning consultant advising individuals, startups, and enterprise clients on strategic and technical AI topics. Mo has successfully managed and executed data science projects with clients across several industries, including cable, auto manufacturing, medical device manufacturing, technology, and car insurance. Previously, he was practice director for AI and deep learning at Think Big Analytics, a Teradata Company, where he mentored and advised Think Big clients and provided guidance on ongoing deep learning projects; he was also a management consultant and a software engineer earlier in his career. A continuous learner, Mo conducts research on applications of deep learning, reinforcement learning, and graph analytics toward solving existing and novel business problems and brings a diversity of educational and hands-on expertise connecting business and technology. He holds an MBA, a master’s degree in computer science, and a bachelor’s degree in mathematics.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)