Presented By O’Reilly and Cloudera
Make Data Work
March 5–6, 2018: Training
March 6–8, 2018: Tutorials & Conference
San Jose, CA

Learning PyTorch by building a recommender system

Mo Patel (Independent), Neejole Patel (Virginia Tech)
9:00am12:30pm Tuesday, March 6, 2018
Secondary topics:  Graphs and Time-series
Average rating: **...
(2.50, 4 ratings)

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 Mo Patel and Neejole Patel walk 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 Mo Patel

Mo Patel

Independent

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.

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.

Comments on this page are now closed.

Comments

Picture of Marcin Jimenez
Marcin Jimenez | DATA SCIENTIST / DATA ARCHITECT
03/06/2018 1:20am PST

I found the cached dataset on google : https://webcache.googleusercontent.com/search?q=cache:dy-Zz0mJaRAJ:https://grouplens.org/datasets/movielens/1m/+&cd=1&hl=en&ct=clnk&gl=us&client=firefox-b-1

Achi Hackmon | CTO
03/05/2018 11:45pm PST

The movielens download doesn’t work