Presented By O’Reilly and Cloudera
Make Data Work
21–22 May 2018: Training
22–24 May 2018: Tutorials & Conference
London, UK

Learning PyTorch by building a recommender system

Neejole Patel (Virginia Tech)
13:3017:00 Tuesday, 22 May 2018
Data science and machine learning
Location: Capital Suite 10 Level: Beginner

Who is this presentation for?

  • Data scientists, data engineers, and application developers

Prerequisite knowledge

  • A working knowledge of Python
  • A basic understanding of deep learning-based modeling and matrix factorization for recommender systems

Materials or downloads needed in advance

What you'll learn

  • Learn how to build deep learning models and deep factorization-based recommendation models using PyTorch

Description

As deep learning has gained popularity and evolved into mainstream software development, there’s been a corresponding rise in frameworks to build deep learning applications. On a simple level, these frameworks can be classified by the define-and-run and define-by-run design patterns. One advantage define-by-run frameworks have is the dynamic nature of the computation graph allowing for flexibility in modeling.

PyTorch, a deep learning framework largely maintained by Facebook, is a design-by-run framework that excels at modeling tasks where flexible inputs are critical, such as natural language processing and event analysis. You’ll gain hands-on experience with PyTorch, as Neejole Patel walks you through using PyTorch to build a content recommendation model.

Outline:

  • PyTorch project and community overview
  • PyTorch basics
  • Understanding automatic differentiation
  • Anatomy of a PyTorch model
  • Modeling data for recommendation using Python tools
  • Matrix factorization in PyTorch
  • Training recommendation models in PyTorch using Movie Lens data
  • PyTorch best practices and tips
  • A look ahead for PyTorch
Photo of Neejole Patel

Neejole Patel

Virginia Tech

Neejole Patel is a sophomore at Virginia Tech, where she is pursuing a BS in computer science with a focus on machine learning, data science, and artificial intelligence. In her free time, Neejole completes independent big data projects, including one that tests the Broken Windows theory using DC crime data. She recently completed an internship at a major home improvement retailer.

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)